Next Article in Journal
Computation Offloading with Privacy-Preserving in Multi-Access Edge Computing: A Multi-Agent Deep Reinforcement Learning Approach
Next Article in Special Issue
A Critical AI View on Autonomous Vehicle Navigation: The Growing Danger
Previous Article in Journal
Digital Forensics for Analyzing Cyber Threats in the XR Technology Ecosystem within Digital Twins
Previous Article in Special Issue
Searching for a Cheap Robust Steering Controller
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Cybersecurity in Autonomous Vehicles—Are We Ready for the Challenge?

by
Irmina Durlik
1,2,*,
Tymoteusz Miller
2,3,4,
Ewelina Kostecka
2,5,
Zenon Zwierzewicz
5 and
Adrianna Łobodzińska
6
1
Faculty of Navigation, Maritime University of Szczecin, Waly Chrobrego 1-2, 70-500 Szczecin, Poland
2
Polish Society of Bioinformatics and Data Science BIODATA, Popiełuszki 4c, 71-214 Szczecin, Poland
3
Institute of Marine and Environmental Sciences, University of Szczecin, Wąska 13, 71-415 Szczecin, Poland
4
Persiaran Perdana BBN, INTI International University, Putra Nilai, Nilai 71800, Malaysia
5
Faculty of Mechatronics and Electrical Engineering, Maritime University of Szczecin, Waly Chrobrego 1-2, 70-500 Szczecin, Poland
6
Institute of Biology, University of Szczecin, Wąska 13, 71-415 Szczecin, Poland
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(13), 2654; https://doi.org/10.3390/electronics13132654
Submission received: 7 June 2024 / Revised: 2 July 2024 / Accepted: 4 July 2024 / Published: 6 July 2024
(This article belongs to the Special Issue Autonomous and Connected Vehicles)

Abstract

:
The rapid development and deployment of autonomous vehicles (AVs) present unprecedented opportunities and challenges in the transportation sector. While AVs promise enhanced safety, efficiency, and convenience, they also introduce significant cybersecurity vulnerabilities due to their reliance on advanced electronics, connectivity, and artificial intelligence (AI). This review examines the current state of cybersecurity in autonomous vehicles, identifying major threats such as remote hacking, sensor manipulation, data breaches, and denial of service (DoS) attacks. It also explores existing countermeasures including intrusion detection systems (IDSs), encryption, over-the-air (OTA) updates, and authentication protocols. Despite these efforts, numerous challenges remain, including the complexity of AV systems, lack of standardization, latency issues, and resource constraints. This review concludes by highlighting future directions in cybersecurity research and development, emphasizing the potential of AI and machine learning, blockchain technology, industry collaboration, and legislative measures to enhance the security of autonomous vehicles.

1. Introduction

The adoption of AVs is anticipated to bring substantial economic and social benefits. By reducing the incidence of human error, which is a leading cause of traffic accidents, AVs can potentially decrease the number of fatalities and injuries on the road. Additionally, the efficiency gains from optimized driving and reduced traffic congestion could lead to lower emissions and fuel consumption. The widespread deployment of AVs could also address mobility challenges for the elderly and disabled, fostering greater inclusivity in transportation [1,2,3].
Despite their promising benefits, autonomous vehicles introduce a host of cybersecurity challenges that must be addressed to ensure their safe and reliable operation. The interconnected nature of AV systems, which rely on continuous data exchange between the vehicle, infrastructure, and external entities, creates a broad attack surface for potential cyber threats. These threats can target various components of the AV ecosystem, including onboard systems, communication networks, and cloud-based services [4,5,6].
Cybersecurity in AVs is critical for several reasons. First, any compromise of an AV’s control systems can have catastrophic consequences, potentially leading to accidents, loss of life, and significant property damage. Second, the theft or manipulation of sensitive data, such as location information and user preferences, poses serious privacy concerns. Third, cyber attacks on AVs could undermine public trust and hinder the widespread adoption of this technology [7,8,9].
Ensuring robust cybersecurity measures in AVs involves a multifaceted approach, including the development of secure software and hardware architectures, implementation of advanced encryption techniques, and continuous monitoring and response to potential threats. It also necessitates collaboration among manufacturers, regulators, and cybersecurity experts to establish industry standards and best practices [10,11].
This review article makes several unique contributions to the body of knowledge in the field of cybersecurity for autonomous vehicles (AVs). While previous reviews have addressed various aspects of AV cybersecurity, our article offers new insights and perspectives that enhance the current understanding and propose innovative solutions for future challenges.
It highlights new and evolving cybersecurity threats specific to AVs that have not been extensively covered in earlier studies. We discuss the potential impact of AI-driven attacks, where malicious actors leverage artificial intelligence to create sophisticated attack vectors that can evade traditional security measures. We also address the increasing threat of advanced sensor spoofing techniques that exploit the complexity of AV sensor systems to manipulate vehicle behavior.
Our article delves into the potential of AI-driven threat detection systems that utilize machine learning algorithms to identify and respond to cyber threats in real time.
This review emphasizes the need for interdisciplinary research that combines cybersecurity with a behavioral analysis of AV systems.
By addressing the multifaceted challenges of AV cybersecurity and proposing innovative solutions, our review aims to enhance public trust in autonomous vehicle technology.
This review not only synthesizes existing knowledge but also introduces new concepts and strategies that advance the field of AV cybersecurity. By identifying emerging threats, exploring cutting-edge countermeasures, and providing comprehensive recommendations for future research and policy, our article adds significant value to the ongoing discourse on securing autonomous vehicles.

2. The Methodology of the Literature Search

In this section, we outline the systematic approach used to conduct our review of cybersecurity challenges and solutions for autonomous vehicles (AVs). The methodology encompasses the selection of search terms, databases, inclusion and exclusion criteria, and the overall review process to ensure a comprehensive and unbiased review.
To capture the broad scope of cybersecurity issues in autonomous vehicles, we utilized a variety of search terms, including “autonomous vehicle cybersecurity”, “connected vehicle threats”, “cybersecurity measures in AVs”, “remote hacking AV”, “sensor manipulation AV”, “data breaches AV”, “DoS attacks AV”, “AI-driven threat detection in AVs”, and “blockchain technology for AV security”. Our search of the literature was conducted across multiple academic and industry databases to ensure a wide range of sources, with primary databases including IEEE Xplore, Google Scholar, PubMed, ACM Digital Library, and ScienceDirect.
To ensure the relevance and quality of the sources, we applied specific inclusion criteria. Articles published between 2015 and 2023 were considered to capture recent advancements and emerging threats. We focused on peer-reviewed journal articles, conference papers, and reputable industry reports to ensure credibility, specifically targeting studies that focused on cybersecurity threats and countermeasures relevant to autonomous vehicles. Conversely, we excluded articles not available in English to ensure comprehension and accuracy, as well as publications that did not substantially discuss cybersecurity in the context of AVs, such as those focusing solely on traditional vehicular security without the context of autonomy.
Our review process began with an initial search and screening, where we performed a comprehensive search using the specified terms across the selected databases. Titles and abstracts of the resulting articles were screened to filter out irrelevant studies. The full texts of the remaining articles were then reviewed to ensure they met the inclusion criteria, with any articles not providing substantial information on AV cybersecurity being excluded at this stage. Key information was extracted from each selected article, focusing on identified threats, countermeasures, challenges, and proposed solutions. These data were organized into thematic categories to facilitate synthesis and comparison.
The extracted data were synthesized to identify common themes, gaps in the existing literature, and emerging trends in AV cybersecurity. A comparative analysis was conducted against previous review articles to highlight the unique contributions of our review. To ensure the robustness of our review, we cross-referenced our findings with established cybersecurity frameworks and guidelines from organizations such as NIST (National Institute of Standards and Technology) and ISO (International Organization for Standardization).
In terms of ethical considerations, we ensured that all data used and referenced in this review were accurately represented and attributed to the original authors. Efforts were made to minimize bias by including a diverse range of sources and perspectives.
By following this rigorous methodology, we aimed to provide a comprehensive and insightful review of the cybersecurity challenges and solutions in the evolving landscape of autonomous vehicles. This methodology ensures that our findings are based on a thorough and systematic examination of the existing literature, contributing valuable insights to the field.

3. Threat Landscape

Remote hacking poses a profound and multifaceted threat to autonomous vehicles (AVs), primarily due to their extensive reliance on wireless communication for crucial functions such as navigation, control, and data exchange. These vehicles utilize a variety of communication channels, including vehicle-to-everything (V2X) systems, cellular networks, and Wi-Fi, to interact with other vehicles, infrastructure, and cloud services. Each of these channels presents potential vulnerabilities that cyber attackers can exploit to gain unauthorized access to the vehicle’s critical systems [12,13,14].
By identifying and exploiting weaknesses in the vehicle’s software architecture or communication protocols, attackers can infiltrate the AV’s network. Once inside, they can execute a range of malicious activities, such as taking control of the vehicle’s steering, acceleration, and braking systems, altering its intended path, or disabling essential safety functions. This level of access can have catastrophic consequences, endangering the lives of passengers and other road users, and can potentially result in large-scale traffic incidents [15,16,17] (Table 1).

3.1. Remote Hacking

Furthermore, remote hacking of AVs has broader implications for the entire transportation ecosystem. Successful cyberattacks can undermine public trust in autonomous vehicle technology, delaying its widespread adoption. The fear of such breaches can also lead to increased regulatory scrutiny and potentially stifle innovation within the industry. The public’s perception of AV safety is crucial, and any high-profile incident can significantly impact the confidence of consumers and stakeholders [22,23,24].
The complexity and integration of numerous subsystems within AVs, such as the control unit, sensor arrays, communication modules, and infotainment systems, exacerbate the challenge of securing these vehicles. Each subsystem must be meticulously protected, and the interactions between them must be continuously monitored to detect and respond to potential threats. This interconnectedness means that a vulnerability in one area can potentially be exploited to gain access to other critical systems, making comprehensive cybersecurity strategies essential [13,15,25].
Effective countermeasures against remote hacking include the implementation of robust encryption protocols, secure software development practices, regular security updates, and advanced intrusion detection systems (IDSs) that can identify and respond to suspicious activities in real time. Additionally, adopting a multi-layered defense approach that incorporates redundancy and failsafe mechanisms can help mitigate the impact of a successful attack [26,27].
In conclusion, remote hacking is a significant and evolving threat to autonomous vehicles, necessitating rigorous and ongoing efforts to enhance cybersecurity measures. As AV technology continues to advance, the industry must prioritize the development and implementation of robust security frameworks to protect these vehicles from the ever-growing landscape of cyber threats (Figure 1).

3.2. Sensor Manipulation

Autonomous vehicles rely extensively on a sophisticated array of sensors, including LiDAR, radar, cameras, and ultrasonic sensors, to accurately perceive and interpret their environment. These sensors provide the critical data needed for navigation, obstacle detection, and decision-making processes. However, the reliance on these sensors also makes AVs vulnerable to sensor manipulation, which encompasses techniques such as spoofing and jamming. Sensor spoofing involves feeding false data into the sensor systems, while jamming disrupts the normal functioning of the sensors by overwhelming them with noise or signals [28,29,30].
Through sensor manipulation, attackers can create deceptive scenarios that lead the vehicle’s control systems to misinterpret the surrounding environment. For example, projecting fake obstacles into the vehicle’s path can cause sudden and unnecessary braking, while concealing real obstacles can lead to collisions. Such manipulations can result in erratic driving behaviors, posing significant safety risks to passengers, other road users, and pedestrians. Additionally, sensor jamming can render the vehicle temporarily blind to its surroundings, forcing it into potentially dangerous situations due to the lack of reliable sensory input [7,9,12,31].
The implications of sensor manipulation extend beyond immediate safety concerns. Persistent threats of sensor attacks can erode public confidence in the safety and reliability of autonomous vehicles, thereby hindering their widespread adoption. Ensuring the integrity and robustness of sensor data is crucial for maintaining trust in AV technology [32,33,34].
Addressing sensor manipulation requires the implementation of advanced detection and mitigation strategies. Robust mechanisms need to be developed to identify anomalies in sensor data that may indicate spoofing or jamming attempts. Techniques such as sensor fusion, where data from multiple sensors are combined and cross-verified, can enhance the reliability of the vehicle’s perception systems. Machine learning algorithms can be employed to detect patterns indicative of sensor manipulation and trigger appropriate countermeasures [28,29,35].
Additionally, the use of redundant sensor systems can provide an extra layer of security. In the event that one sensor is compromised, redundant sensors can help maintain the accuracy and reliability of the vehicle’s perception. Regular updates and maintenance of sensor firmware, along with rigorous testing against potential attack vectors, are also essential components of a comprehensive security strategy [36,37].
In summary, sensor manipulation poses a serious threat to the safe operation of autonomous vehicles. The advanced sensor suites in modern AVs necessitate equally sophisticated mechanisms to detect and counteract such interference. By implementing a combination of sensor fusion, anomaly detection, and redundant systems, the resilience of autonomous vehicles against sensor manipulation can be significantly enhanced, ensuring a safer and more reliable operation.

3.3. Data Breaches

Autonomous vehicles (AVs) generate and process a vast amount of data, encompassing sensitive information such as real-time location, driving patterns, and personal details of the passengers. This extensive data collection is crucial for the functioning and improvement of AV systems, enabling them to navigate accurately, optimize routes, and enhance user experience. However, the sheer volume and sensitivity of these data make AVs prime targets for data breaches [38,39].
Data breaches in the context of AVs can occur through various vectors, including unauthorized access to onboard data storage, interception of communication networks, or exploitation of vulnerabilities in cloud services that support vehicle operations. Cyber attackers may employ techniques such as hacking into the vehicle’s internal systems, intercepting data transmissions between the vehicle and external entities, or exploiting weak security measures in connected infrastructure [40,41].
The consequences of data breaches in AVs are severe and multifaceted. The exposure of sensitive data can lead to significant privacy violations, such as the unauthorized disclosure of passengers’ personal details and real-time tracking of their movements. This can result in identity theft, stalking, and other forms of misuse of personal information. Beyond privacy concerns, compromised data integrity poses a critical risk to the safety and reliability of AVs. If the data guiding an AV’s decision-making processes are altered or corrupted, this can lead to erroneous actions, potentially causing accidents or operational failures [24,42,43].
Moreover, data breaches can have broader implications for the AV industry. Public confidence in the safety and security of autonomous vehicles is vital for their acceptance and widespread adoption. High-profile data breaches can erode this trust, leading to regulatory backlash, legal repercussions, and a slowdown in the advancement and deployment of AV technologies [24,44].
To safeguard against data breaches, it is essential to implement robust cybersecurity measures that ensure the confidentiality, integrity, and availability of data. These measures include the following:
  • Encryption—Employing strong encryption protocols for data both at rest and in transit to prevent unauthorized access [45].
  • Authentication and Access Control—Implementing stringent authentication mechanisms and access control policies to ensure that only authorized personnel and systems can access sensitive data [46].
  • Intrusion Detection Systems (IDSs)—Deploying advanced IDSs to monitor network traffic and detect suspicious activities that may indicate a breach attempt [47].
  • Regular Security Audits—Conducting regular security audits and penetration testing to identify and address potential vulnerabilities in the AV systems [48].
  • Data Anonymization—Anonymizing personal data where possible to minimize the impact of any potential data breach on individual privacy [49].
In conclusion, protecting the extensive and sensitive data associated with autonomous vehicles is paramount to ensuring their safe and reliable operation. By implementing comprehensive cybersecurity strategies, the AV industry can mitigate the risks of data breaches, thereby maintaining public trust and advancing the secure deployment of autonomous vehicle technologies.

3.4. Denial of Service (DoS) Attacks

Denial of service (DoS) attacks represent a significant threat to the normal operation of autonomous vehicles (AVs) by targeting their computational and communication resources. These attacks aim to overwhelm the vehicle’s systems, either by flooding the network with excessive traffic or by exploiting specific vulnerabilities to cause critical components to crash or malfunction. The result is a disruption of the AV’s ability to process data and communicate effectively, which can have severe and immediate consequences [32,33,50].
DoS attacks on AVs can manifest in several ways. Attackers might use network flooding techniques to saturate the vehicle’s communication channels, making it difficult or impossible for the vehicle to send and receive necessary data. This can lead to a loss of connectivity with essential external systems, such as traffic management servers or other vehicles in a vehicle-to-everything (V2X) environment. Another approach involves exploiting software vulnerabilities within the AV’s operating systems or applications, causing critical processes to fail and the vehicle to become unresponsive [51,52,53].
The impact of DoS attacks on AVs can be profound. Degraded performance and loss of connectivity can hinder the vehicle’s ability to navigate safely, as real-time data processing and decision-making are crucial for avoiding obstacles, obeying traffic signals, and maintaining proper speeds. In the worst-case scenario, a successful DoS attack could completely immobilize the vehicle, posing a direct risk to passenger safety and potentially causing traffic disruptions [54,55].
AVs are particularly vulnerable to DoS attacks due to their reliance on continuous, real-time data processing and communication. Any delay or interruption can compromise the vehicle’s ability to operate correctly. Given the high stakes, it is imperative to develop resilient and adaptive systems capable of withstanding DoS attacks [28,56].
To mitigate the risk of DoS attacks, several strategies can be employed as follows:
  • Redundancy and Failover Mechanisms—Implementing redundant communication channels and computational resources can help ensure that the vehicle remains operational even if one pathway is compromised. Failover mechanisms can automatically switch to backup systems in the event of an attack [57].
  • Traffic Filtering and Rate Limiting—Utilizing advanced traffic filtering techniques and rate limiting can help prevent network saturation by identifying and blocking malicious traffic patterns [58].
  • Anomaly Detection System—Deploying anomaly detection systems that monitor network traffic and system behavior in real time can help identify and mitigate DoS attacks before they cause significant disruption. These systems can use machine learning algorithms to recognize unusual patterns indicative of an attack [59].
  • Resource Management—Implementing efficient resource management protocols can ensure that critical systems have the necessary computational power and bandwidth to function correctly, even under attack conditions [60].
  • Regular Security Updates—Ensuring that all software components are regularly updated and patched to fix known vulnerabilities can reduce the risk of exploitation by DoS attacks [61].
In summary, denial of service (DoS) attacks pose a serious threat to the reliability and safety of autonomous vehicles. Given their reliance on real-time data processing and communication, AVs must be equipped with resilient and adaptive systems to withstand such attacks. By implementing a combination of redundancy, traffic filtering, anomaly detection, efficient resource management, and regular updates, the industry can enhance the security and robustness of autonomous vehicles against DoS threats.
Detailed Examples
To provide a clearer understanding of the threats, here are real-world examples of cybersecurity incidents involving AVs:
  • In 2015, researchers Charlie Miller and Chris Valasek demonstrated a remote hack of a Jeep Cherokee, where they gained control over the vehicle’s critical functions such as braking and acceleration through its infotainment system.
  • In 2016, researchers at the University of South Carolina successfully deceived a Tesla Model S’s autopilot system by projecting images that mimicked lane markings, causing the vehicle to veer off its path.
  • In 2020, a cybersecurity firm revealed that hackers could exploit vulnerabilities in the backend servers of several electric vehicle manufacturers, potentially gaining access to user data and vehicle control systems.

4. Existing Countermeasures

To combat the diverse and evolving cybersecurity threats facing autonomous vehicles (AVs), a range of sophisticated cybersecurity strategies have been developed and implemented. These countermeasures aim to protect the vehicle’s critical systems and data from unauthorized access, manipulation, and disruption (Table 2) [62,63].

4.1. Intrusion Detection Systems (IDSs)

Intrusion detection systems (IDSs) play a crucial role in the cybersecurity framework of autonomous vehicles (AVs) by continuously monitoring network traffic and system activities for signs of malicious behavior. These systems are essential for identifying and responding to potential threats in real time, thereby safeguarding the vehicle’s critical systems and data [67,68].
IDSs can be configured to detect a wide range of cyber threats, including unauthorized access attempts, unusual patterns of data traffic, and anomalies that may indicate the presence of malware or other cyber threats. They achieve this through a combination of signature-based detection, which identifies known attack patterns, and anomaly-based detection, which looks for deviations from normal behavior that could signify an unknown threat [69,70].
Advanced IDSs leverage sophisticated analytics and machine learning algorithms to enhance their detection capabilities. These technologies enable IDSs to learn from historical data, recognize complex attack patterns, and adapt to evolving threat landscapes. Machine learning models can identify subtle and previously unseen attack vectors by analyzing large datasets of network traffic and system logs, thereby improving the accuracy and effectiveness of threat detection [68,71,72].
IDSs can be designed as network-based or host-based systems, providing comprehensive coverage across the AV ecosystem.
  • Network-based IDSs (NIDSs)—These systems monitor traffic between devices within the vehicle’s network and between the vehicle and external networks. By analyzing network packets in real time, NIDSs can detect intrusions that attempt to exploit vulnerabilities in communication protocols or launch denial of service attacks. They can also monitor data exchanges between the vehicle and cloud services, ensuring the integrity and security of transmitted data [70,73].
  • Host-based IDSs (HIDSs)—These systems focus on monitoring activities on individual devices or endpoints within the vehicle, such as control units, sensors, and onboard computers. HIDSs can detect suspicious activities at the device level, such as unauthorized changes to system files, unusual process behavior, and attempts to execute malicious code. By providing detailed visibility into the internal operations of each device, HIDSs complement the broader network monitoring capabilities of NIDSs [74].
The integration of IDSs into the cybersecurity architecture of AVs enhances the overall resilience of these vehicles against cyber threats. By providing real-time detection and alerting, IDSs enable the rapid response and mitigation of potential security breaches, minimizing the impact of attacks and ensuring the continued safe operation of autonomous vehicles [75,76,77].
Intrusion detection systems are vital components of the cybersecurity defenses for autonomous vehicles. Their ability to monitor and analyze network and system activities in real time, combined with advanced analytics and machine learning, makes them effective in detecting and responding to a wide range of cyber threats. By implementing both network-based and host-based IDSs, the AV ecosystem can achieve comprehensive protection against potential intrusions and maintain the integrity and security of its operations [78,79,80].

4.2. Encryption

Encryption is a cornerstone of cybersecurity for autonomous vehicles (AVs), playing a crucial role in securing the vast amounts of data these vehicles generate and use. By converting data into a coded format that can only be deciphered by authorized parties, encryption ensures that sensitive information remains protected from unauthorized access during both transmission (data in transit) and storage (data at rest) [81,82,83].
Modern encryption techniques, such as Advanced Encryption Standard (AES) and RSA, provide robust security for communications between the vehicle, infrastructure, and cloud services. AES, a symmetric encryption algorithm, is widely used for its efficiency and strong security properties, making it ideal for encrypting large volumes of data quickly. RSA, an asymmetric encryption algorithm, is often used for secure key exchanges and ensuring that data can be shared securely between parties without the need for a shared secret key [64,84,85].
Encryption safeguards the integrity and confidentiality of critical data, such as navigation instructions, sensor readings, and the personal information of passengers. This protection is vital for several reasons:
  • Preventing Eavesdropping—Encryption ensures that data transmitted between the AV and external systems (such as traffic management servers, other vehicles, and cloud services) are unintelligible to unauthorized entities. This prevents eavesdroppers from intercepting and understanding sensitive information, such as the vehicle’s location or destination [64,86,87].
  • Preventing Data Breaches—In the event of unauthorized access to the vehicle’s data storage systems, encryption ensures that the compromised data remain unusable without the decryption keys. This protects sensitive information, including passenger details and driving patterns, from being exposed and misused [88,89].
  • Maintaining Data Integrity—Encryption helps prevent tampering with the data by ensuring that any unauthorized modifications can be detected. For instance, if an attacker attempts to alter navigation instructions or sensor data, the encryption process will detect these changes, alerting the system to the potential breach [33,42].
  • Enhancing Trust—Robust encryption builds trust among users and stakeholders by ensuring that the AVs handle sensitive information securely. This trust is essential for the widespread adoption of autonomous vehicle technology, as users need confidence that their personal data are protected [64,81].
To implement effective encryption, AV systems must incorporate several best practices.
  • Key Management—Securely managing encryption keys is critical to maintaining the effectiveness of encryption. This involves generating strong keys, securely storing them, and regularly updating them to prevent unauthorized access [90].
  • End-to-End Encryption—Employing end-to-end encryption ensures that data remain encrypted throughout their entire journey, from the point of origin to the final destination. This approach minimizes the risk of data exposure at intermediate points [91].
  • Regular Audits—Conducting regular security audits and assessments helps identify potential weaknesses in the encryption implementation and ensures compliance with the latest security standards [45].
  • Layered Security—Encryption should be part of a multi-layered security approach, complemented by other measures such as authentication, intrusion detection systems, and access control to provide comprehensive protection [25].
Encryption is fundamental to securing the data associated with autonomous vehicles. By protecting data in transit and at rest, encryption safeguards the integrity, confidentiality, and reliability of critical information, preventing eavesdropping, data breaches, and tampering. Implementing robust encryption techniques and best practices is essential for maintaining the security and trustworthiness of autonomous vehicle systems [65].

4.3. Regular Updates

The dynamic nature of cybersecurity threats necessitates regular updates to the software and firmware of autonomous vehicles (AVs). Over-the-air (OTA) updates are a critical tool in this process, enabling manufacturers to remotely deploy security patches, bug fixes, and feature enhancements to AVs without requiring physical access to the vehicle. This capability is essential for promptly addressing newly discovered vulnerabilities and ensuring that the vehicle’s systems remain secure against emerging threats [3,92,93].
Over-the-air (OTA) updates are essential for maintaining the security and functionality of AV systems. Secure OTA update mechanisms ensure that software updates are authenticated and delivered without being tampered with. A notable example is Tesla’s OTA update system, which has successfully delivered critical security patches to its vehicles in response to identified vulnerabilities.
Regular updates help maintain the resilience of AVs by ensuring that their security measures are always up-to-date with the latest advancements and threat intelligence. The importance of regular updates can be understood through several key points:
  • Addressing Vulnerabilities: As cybersecurity researchers and malicious actors continuously discover new vulnerabilities, it is imperative to patch these weaknesses as quickly as possible. OTA updates allow for the rapid deployment of fixes, reducing the window of opportunity for attackers to exploit these vulnerabilities [23].
  • Enhancing Security Features: Regular updates can introduce new security features and improvements, thereby enhancing the overall security posture of the AV. These updates might include advanced encryption methods, improved intrusion detection algorithms, and more robust authentication protocols [72].
  • Bug Fixes: Beyond security vulnerabilities, regular updates address software bugs that could potentially be exploited by attackers or cause system malfunctions. By fixing these bugs, manufacturers ensure the smooth and secure operation of the vehicle’s systems [94].
  • Adapting to Emerging Threats: The cybersecurity landscape is continually evolving, with new threats emerging regularly. OTA updates enable AV manufacturers to adapt to these changes by integrating the latest threat intelligence and defense mechanisms into the vehicle’s software, thereby staying ahead of potential attacks [95].
  • Minimizing Downtime: OTA updates can be scheduled and executed with minimal disruption to the vehicle’s operation, ensuring that the vehicle remains operational while receiving necessary security updates. This minimizes downtime and inconvenience for users [96].
  • Maintaining Compliance: Regulatory bodies may mandate certain security standards and updates for AVs. Regular updates ensure that the vehicles remain compliant with these regulations, avoiding potential legal and financial repercussions [97].
To implement effective regular updates, several best practices should be followed:
  • Secure Update Mechanism: The OTA update process itself must be secure to prevent unauthorized modifications. This includes using strong authentication methods and encryption to protect the integrity and confidentiality of the update files [98].
  • Testing and Validation: Updates should undergo rigorous testing and validation to ensure they do not introduce new vulnerabilities or disrupt existing functionalities. This involves thorough quality assurance processes and possibly phased rollouts [99].
  • User Notification and Consent: Users should be informed about the updates being installed on their vehicles and, where appropriate, provide consent. This transparency helps build trust and ensures that users are aware of the changes being made [100].
  • Regular Update Schedule: Establishing a regular schedule for updates can help ensure that vehicles receive timely security patches and enhancements. While emergency updates should be deployed as needed, a consistent update schedule helps manage the overall maintenance of the vehicle’s software [97].
Regular updates are a fundamental aspect of maintaining the cybersecurity and overall resilience of autonomous vehicles. OTA updates enable rapid, secure, and efficient deployment of security patches, bug fixes, and feature enhancements, ensuring that AVs remain protected against emerging threats and vulnerabilities. By adhering to the best practices for secure and effective updates, manufacturers can enhance the safety, reliability, and user trust in autonomous vehicle technology [45].

4.4. Authentication Protocols

Strong authentication protocols are vital for ensuring that only authorized devices, users, and systems can access and interact with an autonomous vehicle’s network and control systems. These protocols are essential for establishing the identity and legitimacy of entities attempting to communicate with the vehicle, thereby safeguarding the vehicle’s operations and sensitive data from unauthorized access [67,101,102].
Multi-factor authentication (MFA) enhances security by requiring multiple forms of verification before granting access to the vehicle’s systems [100]. Typically, MFA combines two or more of the following factors:
  • Something You Know: a password or PIN.
  • Something You Have: a smart card, token, or mobile device.
  • Something You Are: biometric verification, such as fingerprints or facial recognition.
By requiring multiple forms of authentication, MFA significantly reduces the risk of unauthorized access, as an attacker would need to compromise more than one factor to gain entry [103].
Digital certificates are another critical component of strong authentication protocols. These certificates use public key infrastructure (PKI) to verify the identities of devices and users. When a device or user attempts to connect to the vehicle’s network, the digital certificate confirms their identity through cryptographic techniques. This ensures that only trusted entities can communicate with the vehicle, thereby preventing unauthorized access and potential cyber threats [104,105].
Authentication protocols ensure that only authorized devices, users, and systems can access and interact with AV networks and control systems.
  • Multi-Factor Authentication (MFA): Combines multiple forms of verification, such as passwords, smart cards, and biometric verification, to significantly reduce the risk of unauthorized access.
  • Digital Certificates: Utilize public key infrastructure (PKI) to verify the identities of devices and users, ensuring that communications within the AV ecosystem are secure.
Secure key management practices are crucial for maintaining the integrity of cryptographic operations. This involves generating, distributing, storing, and rotating cryptographic keys securely. Effective key management ensures that keys are not exposed to unauthorized parties and that they are regularly updated to maintain security. Secure key storage mechanisms, such as hardware security modules (HSMs), provide an additional layer of protection for cryptographic keys [99,106].
  • Authentication Protocols in Practice:
    • Vehicle-to-Everything (V2X) Communication: Autonomous vehicles rely on V2X communication to interact with other vehicles, infrastructure, and cloud services. Authentication protocols ensure that all entities involved in V2X communication are legitimate and authorized. For example, vehicles can use digital certificates to authenticate each other and exchange information securely, preventing malicious actors from injecting false data into the network [107,108].
    • Access Control for Onboard Systems: Authentication protocols control access to the vehicle’s onboard systems, such as the infotainment system, navigation, and critical control units. By implementing MFA and digital certificates, only authorized users and devices can interact with these systems, reducing the risk of unauthorized modifications or control [84,109].
    • Software and Firmware Updates: Secure authentication protocols verify the source and integrity of software and firmware updates before they are installed on the vehicle. This prevents malicious updates that could compromise the vehicle’s security. Digital signatures and certificates can be used to authenticate update packages, ensuring that they come from a trusted source [66,110].
    • Remote Access: Autonomous vehicles often support remote access for diagnostics, maintenance, and fleet management. Authentication protocols ensure that only authorized personnel can access the vehicle remotely. MFA and secure key management practices are particularly important in these scenarios to prevent unauthorized remote access [111,112].
  • Preventing Cyber Threats
Robust authentication mechanisms are integral to preventing a range of cyber threats, including the following:
  • Remote Hacking: authentication protocols ensure that only authorized entities can access the vehicle’s network, preventing hackers from gaining control remotely [24].
  • Data Breaches: by verifying the identity of devices and users, authentication protocols protect sensitive data from unauthorized access and theft [7].
  • Spoofing Attacks: digital certificates and secure key management prevent attackers from impersonating legitimate devices or users, ensuring the integrity of communications [39].
Strong authentication protocols are essential for securing autonomous vehicles against unauthorized access and cyber threats. By implementing multi-factor authentication, digital certificates, and secure key management practices, the integrity and security of the vehicle’s systems and data are maintained. These measures are crucial for ensuring the safe and reliable operation of autonomous vehicles in an increasingly connected and complex digital environment.

5. Challenges in Cybersecurity for Autonomous Vehicles

As autonomous vehicles (AVs) become increasingly integrated into modern transportation systems, ensuring their cybersecurity poses significant challenges [113]. These challenges arise from the inherent complexity of AV systems, the current lack of standardization, latency issues, and resource constraints. Addressing these challenges is critical to the safe and reliable operation of AVs (Table 3) [42].

5.1. Complexity of AV Systems

The architecture of autonomous vehicles is highly complex, comprising numerous interconnected subsystems, including sensors, communication modules, control units, and software applications. Each subsystem must operate seamlessly with others to ensure the vehicle functions correctly. This complexity creates multiple potential entry points for cyber attacks, making comprehensive security coverage challenging [116]. The various hardware and software components in an AV must communicate and work together without interruption. Securing each component individually is not enough; their interactions must also be secure. AV systems use a mix of technologies, such as LiDAR, radar, cameras, GPS, and machine learning algorithms. Ensuring that all these technologies are secure requires a multidisciplinary approach to cybersecurity. Regular software and firmware updates are necessary to address new vulnerabilities and enhance functionality, but they also introduce potential risks if not managed securely [72,117,118].
The intricate architecture of AVs involves numerous interconnected subsystems, each with its own vulnerabilities. For example, the integration of LiDAR, radar, cameras, and machine learning algorithms requires secure communication and synchronization, which can be exploited if not properly managed. Regular software and firmware updates are essential but can also introduce new vulnerabilities if not securely implemented.

5.2. Lack of Standardization

The AV industry currently lacks universally accepted standards for cybersecurity. This lack of standardization complicates the implementation of consistent and robust security measures across different manufacturers and models. Without standardized guidelines, manufacturers may adopt different approaches to cybersecurity, leading to inconsistent security levels. Regulations and standards for AV cybersecurity are still evolving, leading to uncertainty and varied compliance requirements across regions and jurisdictions. Additionally, AVs need to communicate with each other and with infrastructure (V2X communication). Standardized security protocols are essential for ensuring secure and reliable interoperability [119,120,121].
Autonomous vehicles rely on real-time data processing and communication to make instantaneous decisions. Cybersecurity measures must be designed to protect these real-time operations without introducing significant latency. Security measures like encryption and authentication protocols can introduce delays. Ensuring that these measures do not compromise the vehicle’s real-time responsiveness is a major challenge. Intrusion detection and response systems must operate with minimal latency to address threats swiftly. Delays in detecting or responding to cyber attacks can lead to catastrophic outcomes. AVs must balance the need for robust security with the performance requirements of real-time operations. Overly complex security measures can hinder the vehicle’s performance [17,95,122].
Ongoing efforts to standardize cybersecurity measures for AVs include initiatives by international bodies such as ISO and SAE. The ISO/SAE 21434 standard, for example, provides guidelines for the cybersecurity lifecycle of road vehicles, from design to decommissioning [119].

5.3. Resource Constraints

Autonomous vehicles have limited computational and energy resources, which must be efficiently managed to support both operational and security needs. Implementing sophisticated cybersecurity measures requires significant processing power. AV systems must ensure that security processes do not overburden the vehicle’s computational resources. Security measures, especially those involving continuous monitoring and real-time data processing, can be energy intensive. Efficient energy management is crucial to maintain the vehicle’s operational range and performance. Integrating advanced cybersecurity features can be costly. Manufacturers must balance the cost of these features with the vehicle’s overall affordability and market competitiveness [3,123,124,125].
Real-time data processing and communication are critical for AV operations. Potential solutions to mitigate latency and resource constraints include the use of edge computing to process data locally, reducing reliance on cloud services, and implementing lightweight cryptographic algorithms to balance security and performance.
The challenges in cybersecurity for autonomous vehicles are multifaceted, involving the complexity of AV systems, lack of standardization, latency issues, and resource constraints. Addressing these challenges requires a holistic and integrated approach to cybersecurity, incorporating robust security practices, standardized protocols, real-time threat detection, and efficient resource management. As the AV industry continues to evolve, ongoing research, collaboration, and regulatory developments will be essential to overcoming these challenges and ensuring the safe and secure operation of autonomous vehicles [1,2,126].

6. Future Directions

As autonomous vehicles (AVs) continue to advance, addressing cybersecurity challenges becomes increasingly critical. Several future directions hold promise for enhancing the security and resilience of AV systems. These include the application of artificial intelligence (AI) and machine learning, the use of blockchain technology, increased industry collaboration and standardization, and progressive legislative and policy developments [127,128].

6.1. AI and Machine Learning Applications

Artificial intelligence and machine learning are poised to play a significant role in the future of AV cybersecurity. These technologies can enhance the ability to detect and respond to cyber threats in real time, adapting to new attack vectors and evolving threat landscapes [129].
  • Threat Detection and Response: AI-driven systems can analyze vast amounts of data from various sensors and network traffic to identify anomalies indicative of cyber threats. Machine learning algorithms can be trained to recognize patterns associated with known attacks and predict potential future threats, enabling proactive defense mechanisms [130].
  • Adaptive Security Systems: Machine learning models can continuously learn from new data, allowing AV security systems to adapt and improve over time. This continuous learning process helps in refining the detection capabilities and reducing false positives, ensuring more accurate and timely responses to genuine threats [131].
  • Automated Mitigation: AI can facilitate automated responses to cyber threats, minimizing human intervention and reducing response times. Automated systems can isolate compromised components, re-route communication, and apply security patches without delay, thereby mitigating the impact of attacks swiftly [132].
  • Anomaly Detection: Machine learning algorithms can analyze vast amounts of data from AV sensors and communication networks to identify deviations from normal behavior, indicating potential cyber threats.
  • Automated Mitigation: AI can facilitate automated responses to detected threats, such as isolating compromised components or re-routing communication paths.

6.2. Blockchain Technology

Blockchain technology offers robust solutions for enhancing the security and integrity of data in AV systems. Its decentralized and immutable nature can address several critical cybersecurity challenges [133].
  • Secure Communication: Blockchain can be used to secure vehicle-to-everything (V2X) communication, ensuring that data exchanged between AVs, infrastructure, and other entities are tamper-proof and authenticated. This can prevent unauthorized access and data manipulation [134].
  • Data Integrity: Blockchain’s immutable ledger ensures that all recorded data are verifiable and cannot be altered retroactively. This is particularly useful for maintaining the integrity of sensor data, driving logs, and software updates, thereby enhancing trust in the system [135].
  • Identity Management: Blockchain can provide a decentralized framework for identity management, ensuring that only authenticated and authorized entities can access AV systems. This reduces the risk of identity spoofing and unauthorized access [136].

6.3. Industry Collaboration and Standardization

Enhanced collaboration among industry stakeholders and the establishment of standardized cybersecurity practices are crucial for the secure development and deployment of AVs [137,138]. Recent collaborative efforts include the formation of the Automotive Information Sharing and Analysis Center (Auto-ISAC), which facilitates the sharing of threat intelligence and best practices among AV manufacturers and cybersecurity experts. Developing and adopting industry-wide standards, such as the ISO/SAE 21434, ensures a consistent level of security across different AV models and manufacturers.
  • Consistent Security Standards: Developing and adopting industry-wide cybersecurity standards can ensure that all AV manufacturers adhere to a baseline level of security, reducing vulnerabilities and inconsistencies across different models and brands [139].
  • Information Sharing: Collaboration among manufacturers, cybersecurity firms, and regulatory bodies can facilitate the sharing of threat intelligence and best practices. This collective approach can help in identifying emerging threats more quickly and developing effective countermeasures [137,140].
  • Joint Research Initiatives: Collaborative research initiatives can drive innovation in AV cybersecurity. By pooling resources and expertise, industry stakeholders can explore new technologies and strategies to enhance the security of AV systems [141].

6.4. Legislative and Policy Developments

Robust legislative and policy frameworks are essential for ensuring the cybersecurity of autonomous vehicles. Governments and regulatory bodies play a critical role in shaping these frameworks [96,142].
Governments and regulatory bodies play a crucial role in shaping the cybersecurity landscape for AVs. Specific legislative measures under consideration include the SELF DRIVE Act in the United States, which mandates cybersecurity measures for AVs, and the European Union’s General Data Protection Regulation (GDPR), which enforces strict data protection standards for AV systems.
  • Regulatory Requirements: Governments can establish stringent cybersecurity requirements for AVs, mandating compliance with specific standards and practices. These regulations can ensure that manufacturers prioritize cybersecurity in the design and deployment of Avs [143,144].
  • Incentives for Security: Policymakers can introduce incentives for manufacturers to invest in advanced cybersecurity technologies and practices. This could include tax breaks, grants, or other financial benefits for companies that demonstrate robust security measures [145,146].
  • Consumer Protection Laws: Legislation can be enacted to protect consumers from cybersecurity risks associated with AVs. This includes laws that ensure transparency in how data are collected, stored, and used, as well as measures to protect personal information from breaches [140,147].
In conclusion, the future of cybersecurity for autonomous vehicles lies in leveraging advanced technologies like AI and blockchain, fostering industry collaboration and standardization, and developing robust legislative and policy frameworks. These directions offer a comprehensive approach to addressing the complex cybersecurity challenges of AVs, ensuring their safe and secure integration into modern transportation systems.

7. Conclusions

In this review, we have explored the critical importance of cybersecurity in the realm of autonomous vehicles (AVs). The key points highlighted include the diverse and significant threats faced by AV systems, such as remote hacking, sensor manipulation, data breaches, and denial of service (DoS) attacks. We have also examined the existing countermeasures deployed to combat these threats, including intrusion detection systems (IDSs), encryption, regular updates, and robust authentication protocols. Furthermore, we have identified the numerous challenges inherent in securing AVs, such as the complexity of AV systems, lack of standardization, latency issues, and resource constraints.
The necessity of ongoing research and collaboration cannot be overstated. The rapidly evolving landscape of cyber threats demands continuous innovation in cybersecurity technologies and practices. Collaborative efforts among AV manufacturers, cybersecurity experts, regulatory bodies, and policymakers are essential to develop and implement effective security measures. Sharing knowledge, standardizing protocols, and conducting joint research initiatives will help in addressing emerging threats and vulnerabilities more efficiently.
Looking to the future, the vision for cybersecurity in autonomous vehicles is one of resilience and adaptability. AI and machine learning will play pivotal roles in developing adaptive security systems capable of real-time threat detection and automated response. Blockchain technology will enhance data integrity and secure communication channels. Industry-wide collaboration and standardization will ensure consistent security practices across all AV platforms. Progressive legislative and policy developments will provide the necessary regulatory framework to enforce robust cybersecurity measures and protect consumers.
The journey towards secure autonomous vehicles is ongoing and multifaceted. By embracing technological advancements, fostering collaboration, and enacting comprehensive policies, we can ensure that AVs are not only innovative but also safe and secure. This holistic approach will pave the way for a future where autonomous vehicles can be trusted to operate reliably, safeguarding both passengers and the broader public.

Author Contributions

Conceptualization, I.D. and T.M.; investigation, A.Ł., I.D., E.K. and T.M.; writing—original draft preparation, A.Ł., I.D., E.K. and T.M.; writing—review and editing, Z.Z., I.D., E.K. and T.M.; visualization, T.M.; supervision, T.M. and Z.Z. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Data Availability Statement

No new data were created.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Parekh, D.; Poddar, N.; Rajpurkar, A.; Chahal, M.; Kumar, N.; Joshi, G.P.; Cho, W. A Review on Autonomous Vehicles: Progress, Methods and Challenges. Electronics 2022, 11, 2162. [Google Scholar] [CrossRef]
  2. Wang, J.; Zhang, L.; Huang, Y.; Zhao, J.; Bella, F. Safety of Autonomous Vehicles. J. Adv. Transp. 2020, 2020, 8867757. [Google Scholar] [CrossRef]
  3. Ahangar, M.N.; Ahmed, Q.Z.; Khan, F.A.; Hafeez, M. A Survey of Autonomous Vehicles: Enabling Communication Technologies and Challenges. Sensors 2021, 21, 706. [Google Scholar] [CrossRef] [PubMed]
  4. Shetty, A.; Yu, M.; Kurzhanskiy, A.; Grembek, O.; Tavafoghi, H.; Varaiya, P. Safety Challenges for Autonomous Vehicles in the Absence of Connectivity. Transp. Res. Part. C Emerg. Technol. 2021, 128, 103133. [Google Scholar] [CrossRef]
  5. Xu, W. From Automation to Autonomy and Autonomous Vehicles. Interactions 2021, 28, 48–53. [Google Scholar] [CrossRef]
  6. Bathla, G.; Bhadane, K.; Singh, R.K.; Kumar, R.; Aluvalu, R.; Krishnamurthi, R.; Kumar, A.; Thakur, R.N.; Basheer, S. Autonomous Vehicles and Intelligent Automation: Applications, Challenges, and Opportunities. Mob. Inf. Syst. 2022, 2022, 7632892. [Google Scholar] [CrossRef]
  7. Kim, K.; Kim, J.S.; Jeong, S.; Park, J.-H.; Kim, H.K. Cybersecurity for Autonomous Vehicles: Review of Attacks and Defense. Comput. Secur. 2021, 103, 102150. [Google Scholar] [CrossRef]
  8. Sharma, P.; Gillanders, J. Cybersecurity and Forensics in Connected Autonomous Vehicles: A Review of the State-of-the-Art. IEEE Access 2022, 10, 108979–108996. [Google Scholar] [CrossRef]
  9. Girdhar, M.; Hong, J.; Moore, J. Cybersecurity of Autonomous Vehicles: A Systematic Literature Review of Adversarial Attacks and Defense Models. IEEE Open J. Veh. Technol. 2023, 4, 417–437. [Google Scholar] [CrossRef]
  10. Algarni, A.; Thayananthan, V. Autonomous Vehicles: The Cybersecurity Vulnerabilities and Countermeasures for Big Data Communication. Symmetry 2022, 14, 2494. [Google Scholar] [CrossRef]
  11. Khalid Khan, S.; Shiwakoti, N.; Stasinopoulos, P.; Warren, M. Modelling Cybersecurity Regulations for Automated Vehicles. Accid. Anal. Prev. 2023, 186, 107054. [Google Scholar] [CrossRef] [PubMed]
  12. Malik, S.; Sun, W. Analysis and Simulation of Cyber Attacks Against Connected and Autonomous Vehicles. In Proceedings of the 2020 International Conference on Connected and Autonomous Driving (MetroCAD), Detroit, MI, USA, 27–28 February 2020; pp. 62–70. [Google Scholar]
  13. Al-Sabaawi, A.; Al-Dulaimi, K.; Foo, E.; Alazab, M. Addressing Malware Attacks on Connected and Autonomous Vehicles: Recent Techniques and Challenges. In Malware Analysis Using Artificial Intelligence and Deep Learning; Springer International Publishing: Cham, Switzerland, 2021; pp. 97–119. [Google Scholar]
  14. Meyer, S.F.; Elvik, R.; Johnsson, E. Risk Analysis for Forecasting Cyberattacks against Connected and Autonomous Vehicles. J. Transp. Secur. 2021, 14, 227–247. [Google Scholar] [CrossRef]
  15. Sharma, O.; Sahoo, N.C.; Puhan, N.B. Recent Advances in Motion and Behavior Planning Techniques for Software Architecture of Autonomous Vehicles: A State-of-the-Art Survey. Eng. Appl. Artif. Intell. 2021, 101, 104211. [Google Scholar] [CrossRef]
  16. Bezai, N.E.; Medjdoub, B.; Al-Habaibeh, A.; Chalal, M.L.; Fadli, F. Future Cities and Autonomous Vehicles: Analysis of the Barriers to Full Adoption. Energy Built Environ. 2021, 2, 65–81. [Google Scholar] [CrossRef]
  17. Khayyam, H.; Javadi, B.; Jalili, M.; Jazar, R.N. Artificial Intelligence and Internet of Things for Autonomous Vehicles. In Nonlinear Approaches in Engineering Applications; Springer International Publishing: Cham, Switzerland, 2020; pp. 39–68. [Google Scholar]
  18. Dash, S.; Azad, C. Cyber Security and Threat Analysis in Autonomous Vehicles. In Autonomous Vehicles Volume 1; Wiley: Hoboken, NJ, USA, 2022; pp. 161–180. [Google Scholar]
  19. Azam, S.; Munir, F.; Sheri, A.M.; Kim, J.; Jeon, M. System, Design and Experimental Validation of Autonomous Vehicle in an Unconstrained Environment. Sensors 2020, 20, 5999. [Google Scholar] [CrossRef] [PubMed]
  20. Frigerio, A.; Vermeulen, B.; Goossens, K.G.W. Automotive Architecture Topologies: Analysis for Safety-Critical Autonomous Vehicle Applications. IEEE Access 2021, 9, 62837–62846. [Google Scholar] [CrossRef]
  21. Sontakke, P.V.; Chopade, N.B. Impact and Analysis of Denial-of-Service Attack on an Autonomous Vehicle Test Bed Setup. In Proceedings of Third International Conference on Intelligent Computing, Information and Control Systems; Springer: Singapore, 2022; pp. 221–236. [Google Scholar]
  22. Rajabli, N.; Flammini, F.; Nardone, R.; Vittorini, V. Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review. IEEE Access 2021, 9, 4797–4819. [Google Scholar] [CrossRef]
  23. Vargas, J.; Alsweiss, S.; Toker, O.; Razdan, R.; Santos, J. An Overview of Autonomous Vehicles Sensors and Their Vulnerability to Weather Conditions. Sensors 2021, 21, 5397. [Google Scholar] [CrossRef] [PubMed]
  24. Khan, S.K.; Shiwakoti, N.; Stasinopoulos, P.; Chen, Y. Cyber-Attacks in the next-Generation Cars, Mitigation Techniques, Anticipated Readiness and Future Directions. Accid. Anal. Prev. 2020, 148, 105837. [Google Scholar] [CrossRef]
  25. Pham, M.; Xiong, K. A Survey on Security Attacks and Defense Techniques for Connected and Autonomous Vehicles. Comput. Secur. 2021, 109, 102269. [Google Scholar] [CrossRef]
  26. Pascale, F.; Adinolfi, E.A.; Coppola, S.; Santonicola, E. Cybersecurity in Automotive: An Intrusion Detection System in Connected Vehicles. Electronics 2021, 10, 1765. [Google Scholar] [CrossRef]
  27. Bangui, H.; Buhnova, B. Recent Advances in Machine-Learning Driven Intrusion Detection in Transportation: Survey. Procedia Comput. Sci. 2021, 184, 877–886. [Google Scholar] [CrossRef]
  28. Wang, Y.; Bian, N.; Zhang, L.; Huang, Y.; Chen, H. Resilient Path-following Control of Autonomous Vehicles Subject to Intermittent Denial-of-service Attacks. IET Intell. Transp. Syst. 2021, 15, 1508–1521. [Google Scholar] [CrossRef]
  29. Dasgupta, S.; Rahman, M.; Islam, M.; Chowdhury, M. A Sensor Fusion-Based GNSS Spoofing Attack Detection Framework for Autonomous Vehicles. IEEE Trans. Intell. Transp. Syst. 2022, 23, 23559–23572. [Google Scholar] [CrossRef]
  30. Chen, L.; He, Y.; Wang, Q.; Pan, W.; Ming, Z. Joint Optimization of Sensing, Decision-Making and Motion-Controlling for Autonomous Vehicles: A Deep Reinforcement Learning Approach. IEEE Trans. Veh. Technol. 2022, 71, 4642–4654. [Google Scholar] [CrossRef]
  31. El-Rewini, Z.; Sadatsharan, K.; Sugunaraj, N.; Selvaraj, D.F.; Plathottam, S.J.; Ranganathan, P. Cybersecurity Attacks in Vehicular Sensors. IEEE Sens. J. 2020, 20, 13752–13767. [Google Scholar] [CrossRef]
  32. Malik, S.; Bandi, P.; Sun, W. An Experimental Study of Denial of Service Attack Against Platoon of Smart Vehicles. In Proceedings of the 2021 Fourth International Conference on Connected and Autonomous Driving (MetroCAD), Detroit, MI, USA, 8–29 April 2021; pp. 23–30. [Google Scholar]
  33. Sun, H.; Peng, C.; Ding, F. Self-discipline Predictive Control of Autonomous Vehicles against Denial of Service Attacks. Asian J. Control 2022, 24, 3538–3551. [Google Scholar] [CrossRef]
  34. Khalid Khan, S.; Shiwakoti, N.; Stasinopoulos, P. A Conceptual System Dynamics Model for Cybersecurity Assessment of Connected and Autonomous Vehicles. Accid. Anal. Prev. 2022, 165, 106515. [Google Scholar] [CrossRef]
  35. Sun, X.; Yu, F.R.; Zhang, P. A Survey on Cyber-Security of Connected and Autonomous Vehicles (CAVs). IEEE Trans. Intell. Transp. Syst. 2022, 23, 6240–6259. [Google Scholar] [CrossRef]
  36. Yang, T.; Lv, C. A Secure Sensor Fusion Framework for Connected and Automated Vehicles Under Sensor Attacks. IEEE Internet Things J. 2022, 9, 22357–22365. [Google Scholar] [CrossRef]
  37. Zhao, X.; Fang, Y.; Min, H.; Wu, X.; Wang, W.; Teixeira, R. Potential Sources of Sensor Data Anomalies for Autonomous Vehicles: An Overview from Road Vehicle Safety Perspective. Expert. Syst. Appl. 2024, 236, 121358. [Google Scholar] [CrossRef]
  38. Channon, M.; Marson, J. THE Liability for Cybersecurity Breaches of Connected and Autonomous Vehicles. Comput. Law. Secur. Rev. 2021, 43, 105628. [Google Scholar] [CrossRef]
  39. Liu, N.; Nikitas, A.; Parkinson, S. Exploring Expert Perceptions about the Cyber Security and Privacy of Connected and Autonomous Vehicles: A Thematic Analysis Approach. Transp. Res. Part. F Traffic Psychol. Behav. 2020, 75, 66–86. [Google Scholar] [CrossRef]
  40. Seetharaman, A.; Patwa, N.; Jadhav, V.; Saravanan, A.S.; Sangeeth, D. Impact of Factors Influencing Cyber Threats on Autonomous Vehicles. Appl. Artif. Intell. 2021, 35, 105–132. [Google Scholar] [CrossRef]
  41. Katrakazas, C.; Theofilatos, A.; Papastefanatos, G.; Härri, J.; Antoniou, C. Cyber Security and Its Impact on CAV Safety: Overview, Policy Needs and Challenges. Adv. Transp. Policy Plan. 2020, 5, 73–94. [Google Scholar]
  42. Kim, S.; Shrestha, R. Automotive Cyber Security; Springer: Singapore, 2020; ISBN 978-981-15-8052-9. [Google Scholar]
  43. Sun, H.-T.; Peng, C.; Ge, X.; Chen, Z. Secure Event-Triggered Sliding Control for Path Following of Autonomous Vehicles Under Sensor and Actuator Attacks. IEEE Trans. Intell. Veh. 2024, 9, 981–992. [Google Scholar] [CrossRef]
  44. Chattopadhyay, A.; Lam, K.-Y.; Tavva, Y. Autonomous Vehicle: Security by Design. IEEE Trans. Intell. Transp. Syst. 2021, 22, 7015–7029. [Google Scholar] [CrossRef]
  45. Benyahya, M.; Collen, A.; Nijdam, N.A. Analyses on Standards and Regulations for Connected and Automated Vehicles: Identifying the Certifications Roadmap. Transp. Eng. 2023, 14, 100205. [Google Scholar] [CrossRef]
  46. Maeng, K.; Kim, W.; Cho, Y. Consumers’ Attitudes toward Information Security Threats against Connected and Autonomous Vehicles. Telemat. Inform. 2021, 63, 101646. [Google Scholar] [CrossRef]
  47. Karopoulos, G.; Kambourakis, G.; Chatzoglou, E.; Hernández-Ramos, J.L.; Kouliaridis, V. Demystifying In-Vehicle Intrusion Detection Systems: A Survey of Surveys and a Meta-Taxonomy. Electronics 2022, 11, 1072. [Google Scholar] [CrossRef]
  48. Mateo Sanguino, T.d.J.; Lozano Domínguez, J.M.; de Carvalho Baptista, P. Cybersecurity Certification and Auditing of Automotive Industry. Adv. Transp. Policy Plan. 2020, 5, 95–124. [Google Scholar]
  49. Panda, S.; Panaousis, E.; Loukas, G.; Kentrotis, K. Privacy Impact Assessment of Cyber Attacks on Connected and Autonomous Vehicles. In Proceedings of the 18th International Conference on Availability, Reliability and Security, Benevento, Italy, 29 August–1 September 2023; ACM: New York, NY, USA, 2023; pp. 1–9. [Google Scholar]
  50. Xiao, S.; Ge, X.; Han, Q.-L.; Zhang, Y. Secure Distributed Adaptive Platooning Control of Automated Vehicles Over Vehicular Ad-Hoc Networks Under Denial-of-Service Attacks. IEEE Trans. Cybern. 2022, 52, 12003–12015. [Google Scholar] [CrossRef] [PubMed]
  51. Alsaade, F.W.; Al-Adhaileh, M.H. Cyber Attack Detection for Self-Driving Vehicle Networks Using Deep Autoencoder Algorithms. Sensors 2023, 23, 4086. [Google Scholar] [CrossRef]
  52. Giannaros, A.; Karras, A.; Theodorakopoulos, L.; Karras, C.; Kranias, P.; Schizas, N.; Kalogeratos, G.; Tsolis, D. Autonomous Vehicles: Sophisticated Attacks, Safety Issues, Challenges, Open Topics, Blockchain, and Future Directions. J. Cybersecur. Priv. 2023, 3, 493–543. [Google Scholar] [CrossRef]
  53. Sun, J.; Xu, G.; Zhang, T.; Cheng, X.; Han, X.; Tang, M. Secure Data Sharing With Flexible Cross-Domain Authorization in Autonomous Vehicle Systems. IEEE Trans. Intell. Transp. Syst. 2023, 24, 7527–7540. [Google Scholar] [CrossRef]
  54. Hu, S.; Yu, W.; Yang, J.; Chen, X.; Xie, X.; Ma, Y. Attack Parameter Dependent Resilient H Path-Following Control Design for Autonomous Vehicles under Cyber Attacks. Control Eng. Pract. 2023, 135, 105488. [Google Scholar] [CrossRef]
  55. Wang, S.; Li, C.; Ng, D.W.K.; Eldar, Y.C.; Poor, H.V.; Hao, Q.; Xu, C. Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification. IEEE Netw. 2023, 37, 16–25. [Google Scholar] [CrossRef]
  56. Cai, X.; Shi, K.; Sun, Y.; Cao, J.; Wen, S.; Qiao, C.; Tian, Z. Stability Analysis of Networked Control Systems Under DoS Attacks and Security Controller Design With Mini-Batch Machine Learning Supervision. IEEE Trans. Inf. Forensics Secur. 2024, 19, 3857–3865. [Google Scholar] [CrossRef]
  57. Verma, P.; Bharot, N.; Breslin, J.G.; Sharma, M.; Chaurasia, N.; Vidyarthi, A. Uncovering Collateral Damages and Advanced Defense Strategies in Cloud Environments against DDoS Attacks: A Comprehensive Review. Trans. Emerg. Telecommun. Technol. 2024, 35, e4934. [Google Scholar] [CrossRef]
  58. Basiri, M.H.; Azad, N.L.; Fischmeister, S. Secure Dynamic Nonlinear Heterogeneous Vehicle Platooning: Denial-of-Service Cyber-Attack Case. In Security in Cyber-Physical Systems; Springer: Cham, Switzerland, 2021; pp. 287–315. [Google Scholar]
  59. Khadka, A.; Karypidis, P.; Lytos, A.; Efstathopoulos, G. A Benchmarking Framework for Cyber-Attacks on Autonomous Vehicles. Transp. Res. Procedia 2021, 52, 323–330. [Google Scholar] [CrossRef]
  60. Nayak, B.P.; Hota, L.; Kumar, A.; Turuk, A.K.; Chong, P.H.J. Autonomous Vehicles: Resource Allocation, Security, and Data Privacy. IEEE Trans. Green Commun. Netw. 2022, 6, 117–131. [Google Scholar] [CrossRef]
  61. Limbasiya, T.; Teng, K.Z.; Chattopadhyay, S.; Zhou, J. A Systematic Survey of Attack Detection and Prevention in Connected and Autonomous Vehicles. Veh. Commun. 2022, 37, 100515. [Google Scholar] [CrossRef]
  62. Chow, M.C.; Ma, M.; Pan, Z. Attack Models and Countermeasures for Autonomous Vehicles. In Intelligent Technologies for Internet of Vehicles; Springe: Cham, Switzerland, 2021; pp. 375–401. [Google Scholar]
  63. Niroumand, F.J.; Ansari Bonab, P.; Sargolzaei, A. Security of Connected and Autonomous Vehicles: A Review of Attacks and Mitigation Strategies. In Proceedings of the SoutheastCon 2024, Atlanta, GA USA, 15 March 2024; pp. 1197–1204. [Google Scholar]
  64. Kim, S.; Shrestha, R. Security and Privacy in Intelligent Autonomous Vehicles. In Automotive Cyber Security; Springer: Singapore, 2020; pp. 35–66. [Google Scholar]
  65. Karim, H.; Rawat, D.B. TollsOnly Please—Homomorphic Encryption for Toll Transponder Privacy in Internet of Vehicles. IEEE Internet Things J. 2022, 9, 2627–2636. [Google Scholar] [CrossRef]
  66. Qureshi, A.; Marvi, M.; Shamsi, J.A.; Aijaz, A. EUF: A Framework for Detecting over-the-Air Malicious Updates in Autonomous Vehicles. J. King Saud. Univ.-Comput. Inf. Sci. 2022, 34, 5456–5467. [Google Scholar] [CrossRef]
  67. Jiang, Q.; Zhang, N.; Ni, J.; Ma, J.; Ma, X.; Choo, K.-K.R. Unified Biometric Privacy Preserving Three-Factor Authentication and Key Agreement for Cloud-Assisted Autonomous Vehicles. IEEE Trans. Veh. Technol. 2020, 69, 9390–9401. [Google Scholar] [CrossRef]
  68. Anthony, C.; Elgenaidi, W.; Rao, M. Intrusion Detection System for Autonomous Vehicles Using Non-Tree Based Machine Learning Algorithms. Electronics 2024, 13, 809. [Google Scholar] [CrossRef]
  69. Abdallah, E.E.; Aloqaily, A.; Fayez, H. Identifying Intrusion Attempts on Connected and Autonomous Vehicles: A Survey. Procedia Comput. Sci. 2023, 220, 307–314. [Google Scholar] [CrossRef]
  70. Aldhyani, T.H.H.; Alkahtani, H. Attacks to Automatous Vehicles: A Deep Learning Algorithm for Cybersecurity. Sensors 2022, 22, 360. [Google Scholar] [CrossRef]
  71. He, Q.; Meng, X.; Qu, R.; Xi, R. Machine Learning-Based Detection for Cyber Security Attacks on Connected and Autonomous Vehicles. Mathematics 2020, 8, 1311. [Google Scholar] [CrossRef]
  72. Jiang, J.; Wang, C.; Chattopadhyay, S.; Zhang, W. Road Context-Aware Intrusion Detection System for Autonomous Cars. In Proceedings of the Information and Communications Security: 21st International Conference, ICICS 2019, Beijing, China, 15–17 December 2019; pp. 124–142. [Google Scholar]
  73. Onur, F.; Gönen, S.; Barışkan, M.A.; Kubat, C.; Tunay, M.; Yılmaz, E.N. Machine Learning-Based Identification of Cybersecurity Threats Affecting Autonomous Vehicle Systems. Comput. Ind. Eng. 2024, 190, 110088. [Google Scholar] [CrossRef]
  74. Baz, M. SEHIDS: Self Evolving Host-Based Intrusion Detection System for IoT Networks. Sensors 2022, 22, 6505. [Google Scholar] [CrossRef]
  75. Yang, L.; Moubayed, A.; Shami, A. MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles. IEEE Internet Things J. 2022, 9, 616–632. [Google Scholar] [CrossRef]
  76. Xie, Y.; Zhou, Y.; Xu, J.; Zhou, J.; Chen, X.; Xiao, F. Cybersecurity Protection on In-vehicle Networks for Distributed Automotive Cyber-physical Systems: State-of-the-art and Future Challenges. Softw. Pract. Exp. 2021, 51, 2108–2127. [Google Scholar] [CrossRef]
  77. Aloqaily, M.; Kanhere, S.; Bellavista, P.; Nogueira, M. Special Issue on Cybersecurity Management in the Era of AI. J. Netw. Syst. Manag. 2022, 30, 39. [Google Scholar] [CrossRef]
  78. Markevych, M.; Dawson, M. A Review of Enhancing Intrusion Detection Systems for Cybersecurity Using Artificial Intelligence (AI). Int. Conf. Knowl.-Based Organ. 2023, 29, 30–37. [Google Scholar] [CrossRef]
  79. Kukkala, V.K.; Thiruloga, S.V.; Pasricha, S. Roadmap for Cybersecurity in Autonomous Vehicles. IEEE Consum. Electron. Mag. 2022, 11, 13–23. [Google Scholar] [CrossRef]
  80. Guan, T.; Han, Y.; Kang, N.; Tang, N.; Chen, X.; Wang, S. An Overview of Vehicular Cybersecurity for Intelligent Connected Vehicles. Sustainability 2022, 14, 5211. [Google Scholar] [CrossRef]
  81. Rathore, M.S.; Poongodi, M.; Saurabh, P.; Lilhore, U.K.; Bourouis, S.; Alhakami, W.; Osamor, J.; Hamdi, M. A Novel Trust-Based Security and Privacy Model for Internet of Vehicles Using Encryption and Steganography. Comput. Electr. Eng. 2022, 102, 108205. [Google Scholar] [CrossRef]
  82. Parekh, R.; Patel, N.; Gupta, R.; Jadav, N.K.; Tanwar, S.; Alharbi, A.; Tolba, A.; Neagu, B.-C.; Raboaca, M.S. GeFL: Gradient Encryption-Aided Privacy Preserved Federated Learning for Autonomous Vehicles. IEEE Access 2023, 11, 1825–1839. [Google Scholar] [CrossRef]
  83. Cui, J.; Yu, J.; Zhong, H.; Wei, L.; Liu, L. Chaotic Map-Based Authentication Scheme Using Physical Unclonable Function for Internet of Autonomous Vehicle. IEEE Trans. Intell. Transp. Syst. 2023, 24, 3167–3181. [Google Scholar] [CrossRef]
  84. Cui, J.; Chen, X.; Zhang, J.; Zhang, Q.; Zhong, H. Toward Achieving Fine-Grained Access Control of Data in Connected and Autonomous Vehicles. IEEE Internet Things J. 2021, 8, 7925–7937. [Google Scholar] [CrossRef]
  85. Murad, S.; Khan, A.; Shiaeles, S.; Masala, G. Data Encryption and Fragmentation in Autonomous Vehicles Using Raspberry Pi 3. In Proceedings of the 2019 IEEE World Congress on Services (SERVICES), Milan, Italy, 8–13 July 2019; pp. 212–216. [Google Scholar]
  86. Ansari, S.; Ahmad, J.; Aziz Shah, S.; Kashif Bashir, A.; Boutaleb, T.; Sinanovic, S. Chaos-based Privacy Preserving Vehicle Safety Protocol for 5G Connected Autonomous Vehicle Networks. Trans. Emerg. Telecommun. Technol. 2020, 31, e3966. [Google Scholar] [CrossRef]
  87. Thing, V.L.L.; Wu, J. Autonomous Vehicle Security: A Taxonomy of Attacks and Defences. In Proceedings of the 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Chengdu, China, 15–18 December 2016; pp. 164–170. [Google Scholar]
  88. Gao, C.; Wang, G.; Shi, W.; Wang, Z.; Chen, Y. Autonomous Driving Security: State of the Art and Challenges. IEEE Internet Things J. 2022, 9, 7572–7595. [Google Scholar] [CrossRef]
  89. Azam, N.; Michala, L.; Ansari, S.; Truong, N.B. Data Privacy Threat Modelling for Autonomous Systems: A Survey From the GDPR’s Perspective. IEEE Trans. Big Data 2023, 9, 388–414. [Google Scholar] [CrossRef]
  90. Jha, S.; Jha, N.; Prashar, D.; Ahmad, S.; Alouffi, B.; Alharbi, A. Integrated IoT-Based Secure and Efficient Key Management Framework Using Hashgraphs for Autonomous Vehicles to Ensure Road Safety. Sensors 2022, 22, 2529. [Google Scholar] [CrossRef]
  91. Hussain, M.; Hong, J.-E. Enforcing Safety in Cooperative Perception of Autonomous Driving Systems through Logistic Chaos Map-Based End-to-End Encryption. In Proceedings of the 2022 16th International Conference on Open Source Systems and Technologies (ICOSST), Lahore, Pakistan, 14 December 2022; pp. 1–6. [Google Scholar]
  92. Ghosal, A.; Halder, S.; Conti, M. STRIDE: Scalable and Secure Over-The-Air Software Update Scheme for Autonomous Vehicles. In Proceedings of the ICC 2020—2020 IEEE International Conference on Communications (ICC), Dublin, Ireland, 7–11 June 2020; pp. 1–6. [Google Scholar]
  93. Feroz, B.; Mehmood, A.; Maryam, H.; Zeadally, S.; Maple, C.; Shah, M.A. Vehicle-Life Interaction in Fog-Enabled Smart Connected and Autonomous Vehicles. IEEE Access 2021, 9, 7402–7420. [Google Scholar] [CrossRef]
  94. Min, H.; Fang, Y.; Wu, X.; Lei, X.; Chen, S.; Teixeira, R.; Zhu, B.; Zhao, X.; Xu, Z. A Fault Diagnosis Framework for Autonomous Vehicles with Sensor Self-Diagnosis. Expert. Syst. Appl. 2023, 224, 120002. [Google Scholar] [CrossRef]
  95. Tan, S.Y.; Taeihagh, A. Adaptive Governance of Autonomous Vehicles: Accelerating the Adoption of Disruptive Technologies in Singapore. Gov. Inf. Q. 2021, 38, 101546. [Google Scholar] [CrossRef]
  96. Ahmed, H.U.; Huang, Y.; Lu, P.; Bridgelall, R. Technology Developments and Impacts of Connected and Autonomous Vehicles: An Overview. Smart Cities 2022, 5, 382–404. [Google Scholar] [CrossRef]
  97. Pek, C.; Manzinger, S.; Koschi, M.; Althoff, M. Using Online Verification to Prevent Autonomous Vehicles from Causing Accidents. Nat. Mach. Intell. 2020, 2, 518–528. [Google Scholar] [CrossRef]
  98. Bouchelaghem, S.; Bouabdallah, A.; Omar, M. Autonomous Vehicle Security: Literature Review of Real Attack Experiments. In Proceedings of the Risks and Security of Internet and Systems: 15th International Conference, CRiSIS 2020, Paris, France, 4–6 November 2020; pp. 255–272. [Google Scholar]
  99. Hu, S.; Zhang, Q.; Weimerskirch, A.; Mao, Z.M. Gatekeeper. In Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security, Nagasaki, Japan, 30 May–3 June 2022; ACM: New York, NY, USA, 2022; pp. 494–507. [Google Scholar]
  100. Martínez-Cruz, A.; Ramírez-Gutiérrez, K.A.; Feregrino-Uribe, C.; Morales-Reyes, A. Security on In-Vehicle Communication Protocols: Issues, Challenges, and Future Research Directions. Comput. Commun. 2021, 180, 1–20. [Google Scholar] [CrossRef]
  101. Miao, J.; Wang, Z.; Ning, X.; Xiao, N.; Cai, W.; Liu, R. Practical and Secure Multifactor Authentication Protocol for Autonomous Vehicles in 5G. Softw. Pract. Exp. 2022, 1–18. [Google Scholar] [CrossRef]
  102. Bagga, P.; Das, A.K.; Wazid, M.; Rodrigues, J.J.P.C.; Park, Y. Authentication Protocols in Internet of Vehicles: Taxonomy, Analysis, and Challenges. IEEE Access 2020, 8, 54314–54344. [Google Scholar] [CrossRef]
  103. Aman, M.N.; Javaid, U.; Sikdar, B. A Privacy-Preserving and Scalable Authentication Protocol for the Internet of Vehicles. IEEE Internet Things J. 2021, 8, 1123–1139. [Google Scholar] [CrossRef]
  104. Vasudev, H.; Deshpande, V.; Das, D.; Das, S.K. A Lightweight Mutual Authentication Protocol for V2V Communication in Internet of Vehicles. IEEE Trans. Veh. Technol. 2020, 69, 6709–6717. [Google Scholar] [CrossRef]
  105. Cui, J.; Chen, Y.; Zhong, H.; He, D.; Wei, L.; Bolodurina, I.; Liu, L. Lightweight Encryption and Authentication for Controller Area Network of Autonomous Vehicles. IEEE Trans. Veh. Technol. 2023, 72, 14756–14770. [Google Scholar] [CrossRef]
  106. Nyangaresi, V.O.; Rodrigues, A.J.; Abeka, S.O. Efficient Group Authentication Protocol for Secure 5G Enabled Vehicular Communications. In Proceedings of the 2020 16th International Computer Engineering Conference (ICENCO), Cairo, Egypt, 29 December 2020; pp. 25–30. [Google Scholar]
  107. Hasan, M.; Mohan, S.; Shimizu, T.; Lu, H. Securing Vehicle-to-Everything (V2X) Communication Platforms. IEEE Trans. Intell. Veh. 2020, 5, 693–713. [Google Scholar] [CrossRef]
  108. Noor-A-Rahim, M.; Liu, Z.; Lee, H.; Khyam, M.O.; He, J.; Pesch, D.; Moessner, K.; Saad, W.; Poor, H.V. 6G for Vehicle-to-Everything (V2X) Communications: Enabling Technologies, Challenges, and Opportunities. Proc. IEEE 2022, 110, 712–734. [Google Scholar] [CrossRef]
  109. Zhang, Q.; Zhong, H.; Cui, J.; Ren, L.; Shi, W. AC4AV: A Flexible and Dynamic Access Control Framework for Connected and Autonomous Vehicles. IEEE Internet Things J. 2021, 8, 1946–1958. [Google Scholar] [CrossRef]
  110. Dafoe, J.; Singh, H.; Chen, N.; Chen, B. Enabling Real-Time Restoration of Compromised ECU Firmware in Connected and Autonomous Vehicles. LNICST 2024, 552, 15–33. [Google Scholar]
  111. Martinho, A.; Herber, N.; Kroesen, M.; Chorus, C. Ethical Issues in Focus by the Autonomous Vehicles Industry. Transp. Rev. 2021, 41, 556–577. [Google Scholar] [CrossRef]
  112. Paddeu, D.; Shergold, I.; Parkhurst, G. The Social Perspective on Policy towards Local Shared Autonomous Vehicle Services (LSAVS). Transp. Policy 2020, 98, 116–126. [Google Scholar] [CrossRef]
  113. Dobryakova, L.; Lemieszewski, L.; Ochin, E. The Vulnerability of Unmanned Vehicles to Terrorist Attacks Such as Global Navigation Satellite System Spoofing. Sci. J. Marit. Univ. Szczec. 2016, 46, 118. [Google Scholar]
  114. Hussain, N.; Rani, P.; Chouhan, H.; Gaur, U.S. Cyber Security and Privacy of Connected and Automated Vehicles (CAVs)-Based Federated Learning: Challenges, Opportunities, and Open Issues. In Federated Learning for IoT Applications; Springer: Cham, Switzerland, 2022; pp. 169–183. [Google Scholar]
  115. Krause, T.; Ernst, R.; Klaer, B.; Hacker, I.; Henze, M. Cybersecurity in Power Grids: Challenges and Opportunities. Sensors 2021, 21, 6225. [Google Scholar] [CrossRef] [PubMed]
  116. Lemieszewski, Ł.; Radomska-Zalas, A.; Perec, A.; Dobryakova, L.; Ochin, E. Gnss and Lnss Positioning of Unmanned Transport Systems: The Brief Classification of Terrorist Attacks on Usvs and Uuvs. Electronics 2021, 10, 401. [Google Scholar] [CrossRef]
  117. Chen, B.; Sun, D.; Zhou, J.; Wong, W.; Ding, Z. A Future Intelligent Traffic System with Mixed Autonomous Vehicles and Human-Driven Vehicles. Inf. Sci. 2020, 529, 59–72. [Google Scholar] [CrossRef]
  118. Grigorescu, S.; Trasnea, B.; Cocias, T.; Macesanu, G. A Survey of Deep Learning Techniques for Autonomous Driving. J. Field Robot. 2020, 37, 362–386. [Google Scholar] [CrossRef]
  119. Das, H.S.; Rahman, M.M.; Li, S.; Tan, C.W. Electric Vehicles Standards, Charging Infrastructure, and Impact on Grid Integration: A Technological Review. Renew. Sustain. Energy Rev. 2020, 120, 109618. [Google Scholar] [CrossRef]
  120. Joubert, N.; Reid, T.G.R.; Noble, F. Developments in Modern GNSS and Its Impact on Autonomous Vehicle Architectures. In Proceedings of the 2020 IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA, 19 October 2020; pp. 2029–2036. [Google Scholar]
  121. Storck, C.R.; Duarte-Figueiredo, F. A Survey of 5G Technology Evolution, Standards, and Infrastructure Associated With Vehicle-to-Everything Communications by Internet of Vehicles. IEEE Access 2020, 8, 117593–117614. [Google Scholar] [CrossRef]
  122. Deveci, M.; Pamucar, D.; Gokasar, I. Fuzzy Power Heronian Function Based CoCoSo Method for the Advantage Prioritization of Autonomous Vehicles in Real-Time Traffic Management. Sustain. Cities Soc. 2021, 69, 102846. [Google Scholar] [CrossRef]
  123. Mehra, A.; Mandal, M.; Narang, P.; Chamola, V. ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions. IEEE Trans. Intell. Transp. Syst. 2021, 22, 4256–4266. [Google Scholar] [CrossRef]
  124. Wang, Y.; Liu, Q.; Mihankhah, E.; Lv, C.; Wang, D. Detection and Isolation of Sensor Attacks for Autonomous Vehicles: Framework, Algorithms, and Validation. IEEE Trans. Intell. Transp. Syst. 2022, 23, 8247–8259. [Google Scholar] [CrossRef]
  125. Hakak, S.; Gadekallu, T.R.; Maddikunta, P.K.R.; Ramu, S.P.; M, P.; De Alwis, C.; Liyanage, M. Autonomous Vehicles in 5G and beyond: A Survey. Veh. Commun. 2023, 39, 100551. [Google Scholar] [CrossRef]
  126. Hataba, M.; Sherif, A.; Mahmoud, M.; Abdallah, M.; Alasmary, W. Security and Privacy Issues in Autonomous Vehicles: A Layer-Based Survey. IEEE Open J. Commun. Soc. 2022, 3, 811–829. [Google Scholar] [CrossRef]
  127. Cao, D.; Wang, X.; Li, L.; Lv, C.; Na, X.; Xing, Y.; Li, X.; Li, Y.; Chen, Y.; Wang, F.-Y. Future Directions of Intelligent Vehicles: Potentials, Possibilities, and Perspectives. IEEE Trans. Intell. Veh. 2022, 7, 7–10. [Google Scholar] [CrossRef]
  128. Gul, F.; Mir, I.; Abualigah, L.; Sumari, P.; Forestiero, A. A Consolidated Review of Path Planning and Optimization Techniques: Technical Perspectives and Future Directions. Electronics 2021, 10, 2250. [Google Scholar] [CrossRef]
  129. Soori, M.; Arezoo, B.; Dastres, R. Artificial Intelligence, Machine Learning and Deep Learning in Advanced Robotics, a Review. Cogn. Robot. 2023, 3, 54–70. [Google Scholar] [CrossRef]
  130. Bachute, M.R.; Subhedar, J.M. Autonomous Driving Architectures: Insights of Machine Learning and Deep Learning Algorithms. Mach. Learn. Appl. 2021, 6, 100164. [Google Scholar] [CrossRef]
  131. Ullah, Z.; Al-Turjman, F.; Mostarda, L.; Gagliardi, R. Applications of Artificial Intelligence and Machine Learning in Smart Cities. Comput. Commun. 2020, 154, 313–323. [Google Scholar] [CrossRef]
  132. Jing, P.; Hu, H.; Zhan, F.; Chen, Y.; Shi, Y. Agent-Based Simulation of Autonomous Vehicles: A Systematic Literature Review. IEEE Access 2020, 8, 79089–79103. [Google Scholar] [CrossRef]
  133. Narbayeva, S.; Bakibayev, T.; Abeshev, K.; Makarova, I.; Shubenkova, K.; Pashkevich, A. Blockchain Technology on the Way of Autonomous Vehicles Development. Transp. Res. Procedia 2020, 44, 168–175. [Google Scholar] [CrossRef]
  134. Nair, M.M.; Tyagi, A.K. Preserving Privacy Using Blockchain Technology in Autonomous Vehicles. In Proceedings of International Conference on Network Security and Blockchain Technology; Springer: Singapore, 2022; pp. 237–248. [Google Scholar]
  135. Kamble, N.; Gala, R.; Vijayaraghavan, R.; Shukla, E.; Patel, D. Using Blockchain in Autonomous Vehicles. In Artificial Intelligence and Blockchain for Future Cybersecurity Applications; Springer: Cham, Switzerland, 2021; pp. 285–305. [Google Scholar]
  136. Gupta, R.; Tanwar, S.; Kumar, N.; Tyagi, S. Blockchain-Based Security Attack Resilience Schemes for Autonomous Vehicles in Industry 4.0: A Systematic Review. Comput. Electr. Eng. 2020, 86, 106717. [Google Scholar] [CrossRef]
  137. Almeaibed, S.; Al-Rubaye, S.; Tsourdos, A.; Avdelidis, N.P. Digital Twin Analysis to Promote Safety and Security in Autonomous Vehicles. IEEE Commun. Stand. Mag. 2021, 5, 40–46. [Google Scholar] [CrossRef]
  138. Lee, D.; Hess, D.J. Regulations for On-Road Testing of Connected and Automated Vehicles: Assessing the Potential for Global Safety Harmonization. Transp. Res. Part. A Policy Pract. 2020, 136, 85–98. [Google Scholar] [CrossRef]
  139. Omeiza, D.; Webb, H.; Jirotka, M.; Kunze, L. Explanations in Autonomous Driving: A Survey. IEEE Trans. Intell. Transp. Syst. 2022, 23, 10142–10162. [Google Scholar] [CrossRef]
  140. Alawadhi, M.; Almazrouie, J.; Kamil, M.; Khalil, K.A. Review and Analysis of the Importance of Autonomous Vehicles Liability: A Systematic Literature Review. Int. J. Syst. Assur. Eng. Manag. 2020, 11, 1227–1249. [Google Scholar] [CrossRef]
  141. Vermesan, O.; John, R.; Pype, P.; Daalderop, G.; Kriegel, K.; Mitic, G.; Lorentz, V.; Bahr, R.; Sand, H.E.; Bockrath, S.; et al. Automotive Intelligence Embedded in Electric Connected Autonomous and Shared Vehicles Technology for Sustainable Green Mobility. Front. Future Transp. 2021, 2, 688482. [Google Scholar] [CrossRef]
  142. Lu, Y.; Ma, H.; Smart, E.; Yu, H. Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review. IEEE Trans. Intell. Transp. Syst. 2022, 23, 6082–6100. [Google Scholar] [CrossRef]
  143. Sohrabi, S.; Khreis, H.; Lord, D. Impacts of Autonomous Vehicles on Public Health: A Conceptual Model and Policy Recommendations. Sustain. Cities Soc. 2020, 63, 102457. [Google Scholar] [CrossRef]
  144. Wang, H.; Khajepour, A.; Cao, D.; Liu, T. Ethical Decision Making in Autonomous Vehicles: Challenges and Research Progress. IEEE Intell. Transp. Syst. Mag. 2022, 14, 6–17. [Google Scholar] [CrossRef]
  145. Othman, K. Exploring the Implications of Autonomous Vehicles: A Comprehensive Review. Innov. Infrastruct. Solut. 2022, 7, 165. [Google Scholar] [CrossRef]
  146. Xing, Y.; Lv, C.; Cao, D.; Hang, P. Toward Human-Vehicle Collaboration: Review and Perspectives on Human-Centered Collaborative Automated Driving. Transp. Res. Part. C Emerg. Technol. 2021, 128, 103199. [Google Scholar] [CrossRef]
  147. Benyahya, M.; Collen, A.; Kechagia, S.; Nijdam, N.A. Automated City Shuttles: Mapping the Key Challenges in Cybersecurity, Privacy and Standards to Future Developments. Comput. Secur. 2022, 122, 102904. [Google Scholar] [CrossRef]
Figure 1. Autonomous vehicle ecosystem and cybersecurity threats.
Figure 1. Autonomous vehicle ecosystem and cybersecurity threats.
Electronics 13 02654 g001
Table 1. Common cyber threats to autonomous vehicles and their impacts.
Table 1. Common cyber threats to autonomous vehicles and their impacts.
Threat TypeDescriptionReal-World ExamplesPotential Impacts
Remote HackingUnauthorized access to vehicle systems via wireless communicationJeep Cherokee hack (2015)Vehicle control takeover, disabling functions, safety risks [18]
Sensor ManipulationInterference with sensors like LiDAR, radar, camerasTesla autopilot deception (2016)False obstacle detection, erratic behavior, collisions [19]
Data BreachesUnauthorized access to sensitive data stored or transmitted by the vehicleElectric vehicle manufacturer server hack (2020)Privacy violations, identity theft, compromised decision-making [20]
DoS AttacksOverloading vehicle’s systems to disrupt normal operationsDDoS attacks on vehicle-to-infrastructure networksPerformance degradation, connectivity loss, vehicle immobilization [21]
Table 2. Existing countermeasures in AV cybersecurity.
Table 2. Existing countermeasures in AV cybersecurity.
CountermeasureDescriptionBenefits
Intrusion Detection SystemsMonitoring network traffic for malicious activityReal-time threat detection, anomaly identification [64]
EncryptionSecuring data in transit and at restProtects data integrity and confidentiality [65]
Regular UpdatesOTA updates for software and firmwareAddresses vulnerabilities, enhances functionality [66]
Authentication ProtocolsEnsuring only authorized access to vehicle systemsPrevents unauthorized access, secures communication [12]
Table 3. Challenges in AV cybersecurity.
Table 3. Challenges in AV cybersecurity.
ChallengeDescriptionExamples
Complexity of AV SystemsNumerous interconnected subsystems and technologiesLiDAR radar, GPS, machine learning [52]
Lack of StandardizationNo universally accepted cybersecurity standardsVaried security practices, regulatory gaps [114]
Latency IssuesReal-time data processing and communication requirementsEncryption delays, threat detection latency [20]
Resource ConstraintsLimited computational and energy resourcesProcessing power, energy consumption, cost constraints [115]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Durlik, I.; Miller, T.; Kostecka, E.; Zwierzewicz, Z.; Łobodzińska, A. Cybersecurity in Autonomous Vehicles—Are We Ready for the Challenge? Electronics 2024, 13, 2654. https://doi.org/10.3390/electronics13132654

AMA Style

Durlik I, Miller T, Kostecka E, Zwierzewicz Z, Łobodzińska A. Cybersecurity in Autonomous Vehicles—Are We Ready for the Challenge? Electronics. 2024; 13(13):2654. https://doi.org/10.3390/electronics13132654

Chicago/Turabian Style

Durlik, Irmina, Tymoteusz Miller, Ewelina Kostecka, Zenon Zwierzewicz, and Adrianna Łobodzińska. 2024. "Cybersecurity in Autonomous Vehicles—Are We Ready for the Challenge?" Electronics 13, no. 13: 2654. https://doi.org/10.3390/electronics13132654

APA Style

Durlik, I., Miller, T., Kostecka, E., Zwierzewicz, Z., & Łobodzińska, A. (2024). Cybersecurity in Autonomous Vehicles—Are We Ready for the Challenge? Electronics, 13(13), 2654. https://doi.org/10.3390/electronics13132654

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop