sustainability-logo

Journal Browser

Journal Browser

Advances in Machine Learning Technology in Information and Cyber Security

A special issue of Sustainability (ISSN 2071-1050).

Deadline for manuscript submissions: closed (31 August 2023) | Viewed by 21819

Special Issue Editors


E-Mail Website
Guest Editor
Department of Information and Computer Engineering, Chung Yuan Christian University, Taoyuan, Taiwan
Interests: network security; digital forensics; secure payment; communications security
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Thiagarajar College of Engineering, Madurai 625015, India
Interests: network security; digital forensics; IoT

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Thiagarajar College of Engineering, Madurai 625015, India
Interests: AI; machine learning; information security

Special Issue Information

Dear Colleagues,

Due to the rapid spread of sensors and mobile devices, we have been experiencing a new revolution in communication in recent years. Every firm now places a high focus on cyber security. The proper controls and processes must be put in place in order to detect such attacks and protect against them. However, there will always be more cyberattacks than people attempting to defend themselves from them. Daily risks are being found, making it more difficult for present solutions to handle a lot of data to analyze.

Cyber security and the detection of cyberthreats could greatly benefit from the advancement of artificial intelligence (AI). Machine learning algorithms can be trained to look for assaults that resemble other types of attacks. By doing so, we are able to identify even the first of their sort of breach and create improved security measures.

Machine learning techniques have shown to be advantageous for the entire security business, i.e., they can aid in the automatic learning of information from data sources and lessen the workload of analysts. Deep face recognition and natural language processing are two further areas where cutting-edge methods such as reinforcement learning and deep learning can be employed. However, the lack of standardized datasets, overfitting difficulties, the cost of the architecture, and other factors frequently restrict the implementation of machine learning. Thus, it is crucial to implement and create new strategies in order to keep the advantages of machine learning algorithms while addressing the practical constraints.

This Special Issue will focus on the cutting-edge research from both academia and industry, and it aims to solicit original research papers with a particular emphasis on the challenges and future trends in cyber security with machine learning applications.

Potential topics include, but are not limited to, the following:

  • Cyber security management in cyber-physical systems using AI;
  • Security, privacy, and trust issues in cyber-physical systems;
  • Blockchain-enabled cyber-physical systems;
  • Utilizing AI technologies for cyber investigation and threat intelligence;
  • The integration of AI and blockchains for security critical infrastructures;
  • Design, optimization, and modeling of cyber security management systems;
  • AI and ML for intrusion detection/prevention in sensitive environments;
  • Advanced AI techniques to secure future Internet architectures/protocols;
  • Trust management in cyber-physical networks and systems;
  • Privacy management at the edge of the network using machine learning;
  • Trustworthy data collection and processing using intelligent learning techniques;
  • Cyber security management of big data;
  • AI-based cyber security techniques for IoT, IoE, IoH, and IoV;
  • Cyber security of connected and autonomous vehicles;
  • Cyber security and AI for digital twins;
  • Management framework for intelligent secure networking;
  • Cyber security management to protect organizations’ sensitive data using intelligent learning techniques;
  • AI-enabled digital investigation.

Prof. Dr. Ming Hour Yang
Prof. Dr. Vijayalakshmi Murugesan
Prof. Dr. Mercy Shalinie Selvaraj
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sustainability is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • cyber security management in cyber-physical systems using AI
  • security, privacy, and trust issues in cyber-physical systems
  • blockchain-enabled cyber-physical systems
  • utilizing AI technologies for cyber investigation and threat intelligence
  • the integration of AI and blockchains for security critical infrastructures
  • design, optimization, and modeling of cyber security management systems
  • AI and ML for intrusion detection/prevention in sensitive environments
  • advanced AI techniques to secure future Internet architectures/protocols
  • trust management in cyber-physical networks and systems
  • privacy management at the edge of the network using machine learning
  • trustworthy data collection and processing using intelligent learning techniques
  • cyber security management of big data
  • AI-based cyber security techniques for IoT, IoE, IoH, and IoV
  • cyber security of connected and autonomous vehicles
  • cyber security and AI for digital twins
  • management framework for intelligent secure networking
  • cyber security management to protect organizations’ sensitive data using intelligent learning techniques
  • AI-enabled digital investigation

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 8811 KiB  
Article
Blockchain-Assisted Machine Learning with Hybrid Metaheuristics-Empowered Cyber Attack Detection and Classification Model
by Ashwag Albakri, Bayan Alabdullah and Fatimah Alhayan
Sustainability 2023, 15(18), 13887; https://doi.org/10.3390/su151813887 - 19 Sep 2023
Cited by 4 | Viewed by 1313
Abstract
Cyber attack detection is the process of detecting and responding to malicious or unauthorized activities in networks, computer systems, and digital environments. The objective is to identify these attacks early, safeguard sensitive data, and minimize the potential damage. An intrusion detection system (IDS) [...] Read more.
Cyber attack detection is the process of detecting and responding to malicious or unauthorized activities in networks, computer systems, and digital environments. The objective is to identify these attacks early, safeguard sensitive data, and minimize the potential damage. An intrusion detection system (IDS) is a cybersecurity tool mainly designed to monitor system activities or network traffic to detect and respond to malicious or suspicious behaviors that may indicate a cyber attack. IDSs that use machine learning (ML) and deep learning (DL) have played a pivotal role in helping organizations identify and respond to security risks in a prompt manner. ML and DL techniques can analyze large amounts of information and detect patterns that may indicate the presence of malicious or cyber attack activities. Therefore, this study focuses on the design of blockchain-assisted hybrid metaheuristics with a machine learning-based cyber attack detection and classification (BHMML-CADC) algorithm. The BHMML-CADC method focuses on the accurate recognition and classification of cyber attacks. Moreover, the BHMML-CADC technique applies Ethereum BC for attack detection. In addition, a hybrid enhanced glowworm swarm optimization (HEGSO) system is utilized for feature selection (FS). Moreover, cyber attacks can be identified with the design of a quasi-recurrent neural network (QRNN) model. Finally, hunter–prey optimization (HPO) algorithm is used for the optimal selection of the QRNN parameters. The experimental outcomes of the BHMML-CADC system were validated on the benchmark BoT-IoT dataset. The wide-ranging simulation analysis illustrates the superior performance of the BHMML-CADC method over other algorithms, with a maximum accuracy of 99.74%. Full article
Show Figures

Figure 1

16 pages, 1911 KiB  
Article
Machine Learning for APT Detection
by Abdullah Said AL-Aamri, Rawad Abdulghafor, Sherzod Turaev, Imad Al-Shaikhli, Akram Zeki and Shuhaili Talib
Sustainability 2023, 15(18), 13820; https://doi.org/10.3390/su151813820 - 16 Sep 2023
Viewed by 3308
Abstract
Nowadays, countries face a multitude of electronic threats that have permeated almost all business sectors, be it private corporations or public institutions. Among these threats, advanced persistent threats (APTs) stand out as a well-known example. APTs are highly sophisticated and stealthy computer network [...] Read more.
Nowadays, countries face a multitude of electronic threats that have permeated almost all business sectors, be it private corporations or public institutions. Among these threats, advanced persistent threats (APTs) stand out as a well-known example. APTs are highly sophisticated and stealthy computer network attacks meticulously designed to gain unauthorized access and persist undetected threats within targeted networks for extended periods. They represent a formidable cybersecurity challenge for governments, corporations, and individuals alike. Recognizing the gravity of APTs as one of the most critical cybersecurity threats, this study aims to reach a deeper understanding of their nature and propose a multi-stage framework for automated APT detection leveraging time series data. Unlike previous models, the proposed approach has the capability to detect real-time attacks based on stored attack scenarios. This study conducts an extensive review of existing research, identifying its strengths, weaknesses, and opportunities for improvement. Furthermore, standardized techniques have been enhanced to enhance their effectiveness in detecting APT attacks. The learning process relies on datasets sourced from various channels, including journal logs, traceability audits, and systems monitoring statistics. Subsequently, an efficient APT detection and prevention system, known as the composition-based decision tree (CDT), has been developed to operate in complex environments. The obtained results demonstrate that the proposed approach consistently outperforms existing algorithms in terms of detection accuracy and effectiveess. Full article
Show Figures

Figure 1

24 pages, 2214 KiB  
Article
Applying Transfer Learning Approaches for Intrusion Detection in Software-Defined Networking
by Hsiu-Min Chuang and Li-Jyun Ye
Sustainability 2023, 15(12), 9395; https://doi.org/10.3390/su15129395 - 11 Jun 2023
Cited by 4 | Viewed by 1887
Abstract
In traditional network management, the configuration of routing policies and associated settings on individual routers and switches was performed manually, incurring a considerable cost. By centralizing network management, software-defined networking (SDN) technology has reduced hardware construction costs and increased flexibility. However, this centralized [...] Read more.
In traditional network management, the configuration of routing policies and associated settings on individual routers and switches was performed manually, incurring a considerable cost. By centralizing network management, software-defined networking (SDN) technology has reduced hardware construction costs and increased flexibility. However, this centralized architecture renders information security vulnerable to network attacks, making intrusion detection in the SDN environment crucial. Machine-learning approaches have been widely used for intrusion detection recently. However, critical issues such as unknown attacks, insufficient data, and class imbalance may significantly affect the performance of typical machine learning. We addressed these problems and proposed a transfer-learning method based on the SDN environment. The following experimental results showed that our method outperforms typical machine learning methods. (1) our model achieved a F1-score of 0.71 for anomaly detection for unknown attacks; (2) for small samples, our model achieved a F1-score of 0.98 for anomaly detection and a F1-score of 0.51 for attack types identification; (3) for class imbalance, our model achieved an F1-score of 1.00 for anomaly detection and 0.91 for attack type identification. In addition, our model required 15,230 seconds (4 h 13 m 50 s) for training, ranking second among the six models when considering both performance and efficiency. In future studies, we plan to combine sampling techniques with few-shot learning to improve the performance of minority classes in class imbalance scenarios. Full article
Show Figures

Figure 1

26 pages, 7250 KiB  
Article
Hybrid Multichannel-Based Deep Models Using Deep Features for Feature-Oriented Sentiment Analysis
by Waqas Ahmad, Hikmat Ullah Khan, Tasswar Iqbal, Muhammad Attique Khan, Usman Tariq and Jae-hyuk Cha
Sustainability 2023, 15(9), 7213; https://doi.org/10.3390/su15097213 - 26 Apr 2023
Cited by 1 | Viewed by 1392
Abstract
With the rapid growth of user-generated content on social media, several new research domains have emerged, and sentiment analysis (SA) is one of the active research areas due to its significance. In the field of feature-oriented sentiment analysis, both convolutional neural network (CNN) [...] Read more.
With the rapid growth of user-generated content on social media, several new research domains have emerged, and sentiment analysis (SA) is one of the active research areas due to its significance. In the field of feature-oriented sentiment analysis, both convolutional neural network (CNN) and gated recurrent unit (GRU) performed well. The former is widely used for local feature extraction, whereas the latter is suitable for extracting global contextual information or long-term dependencies. In existing studies, the focus has been to combine them as a single framework; however, these approaches fail to fairly distribute the features as inputs, such as word embedding, part-of-speech (PoS) tags, dependency relations, and contextual position information. To solve this issue, in this manuscript, we propose a technique that combines variant algorithms in a parallel manner and treats them equally to extract advantageous informative features, usually known as aspects, and then performs sentiment classification. Thus, the proposed methodology combines a multichannel convolutional neural network (MC-CNN) with a multichannel bidirectional gated recurrent unit (MC-Bi-GRU) and provides them with equal input parameters. In addition, sharing the information of hidden layers between parallelly combined algorithms becomes another cause of achieving the benefits of their combined abilities. These abilities make this approach distinctive and novel compared to the existing methodologies. An extensive empirical analysis carried out on several standard datasets confirms that the proposed technique outperforms the latest existing models. Full article
Show Figures

Figure 1

17 pages, 4161 KiB  
Article
Twitter Bot Detection Using Diverse Content Features and Applying Machine Learning Algorithms
by Fawaz Khaled Alarfaj, Hassaan Ahmad, Hikmat Ullah Khan, Abdullah Mohammaed Alomair, Naif Almusallam and Muzamil Ahmed
Sustainability 2023, 15(8), 6662; https://doi.org/10.3390/su15086662 - 14 Apr 2023
Cited by 4 | Viewed by 3973
Abstract
A social bot is an intelligent computer program that acts like a human and carries out various activities in a social network. A Twitter bot is one of the most common forms of social bots. The detection of Twitter bots has become imperative [...] Read more.
A social bot is an intelligent computer program that acts like a human and carries out various activities in a social network. A Twitter bot is one of the most common forms of social bots. The detection of Twitter bots has become imperative to draw lines between real and unreal Twitter users. In this research study, the main aim is to detect Twitter bots based on diverse content-specific feature sets and explore the use of state-of-the-art machine learning classifiers. The real-world data from Twitter is scrapped using Twitter API and is pre-processed using standard procedure. To analyze the content of tweets, several feature sets are proposed, such as message-based, part-of-speech, special characters, and sentiment-based feature sets. Min-max normalization is considered for data normalization and then feature selection methods are applied to rank the top features within each feature set. For empirical analysis, robust machine learning algorithms such as deep learning (DL), multilayer perceptron (MLP), random forest (RF), naïve Bayes (NB), and rule-based classification (RBC) are applied. The performance evaluation based on standard metrics of precision, accuracy, recall, and f-measure reveals that the proposed approach outperforms the existing studies in the relevant literature. In addition, we explore the effectiveness of each feature set for the detection of Twitter bots. Full article
Show Figures

Figure 1

16 pages, 7834 KiB  
Article
Blockchain-Driven Image Encryption Process with Arithmetic Optimization Algorithm for Security in Emerging Virtual Environments
by Manal Abdullah Alohali, Mohammed Aljebreen, Fuad Al-Mutiri, Mahmoud Othman, Abdelwahed Motwakel, Mohamed Ibrahim Alsaid, Amani A. Alneil and Azza Elneil Osman
Sustainability 2023, 15(6), 5133; https://doi.org/10.3390/su15065133 - 14 Mar 2023
Cited by 6 | Viewed by 1626
Abstract
The real world is bounded by people, hospitals, industries, buildings, businesses, vehicles, cognitive cities, and billions of devices that offer various services and interact with the world. Recent technologies, including AR, VR, XR, and the digital twin concept, provide advanced solutions to create [...] Read more.
The real world is bounded by people, hospitals, industries, buildings, businesses, vehicles, cognitive cities, and billions of devices that offer various services and interact with the world. Recent technologies, including AR, VR, XR, and the digital twin concept, provide advanced solutions to create a new virtual world. Due to the ongoing development of information communication technologies and broadcast channels, data security has become a major concern. Blockchain (BC) technology is an open, decentralized, and transparent distributed database that can be maintained by the group. BC’s major features are high credibility, decentralization, transparency, versatility, autonomy, traceability, anonymity, intelligence, reward mechanisms, and irreversibility. This study presents a blockchain-driven image encryption technique using arithmetic optimization with a fractional-order Lorenz system (BDIE-AOFOLS). The BDIE-AOFOLS technique uses the FOLS method, which integrates the Arnold map, tent map, and fractional Lorenz system. Besides this, an arithmetic optimization algorithm (AOA) was carried out for the optimum key generation process to achieve the maximum PSNR value. The design of an AOA-based optimal generation of keys for the FOLS technique determines the novelty of the current work. Moreover, the cryptographical pixel values of the images can be stored securely in the BC, guaranteeing image security. We compared the outcomes of the proposed BDIE-AOFOLS technique against benchmark color images. The comparative analysis demonstrated the improved security efficiency of the BDIE-AOFOLS technique over other approaches, with a mean square error of 0.0430 and a peak signal-to-noise ratio of 61.80 dB. Full article
Show Figures

Figure 1

15 pages, 3737 KiB  
Article
Modelling of Metaheuristics with Machine Learning-Enabled Cybersecurity in Unmanned Aerial Vehicles
by Mohammed Rizwanullah, Hanan Abdullah Mengash, Mohammad Alamgeer, Khaled Tarmissi, Amira Sayed A. Aziz, Amgad Atta Abdelmageed, Mohamed Ibrahim Alsaid and Mohamed I. Eldesouki
Sustainability 2022, 14(24), 16741; https://doi.org/10.3390/su142416741 - 14 Dec 2022
Cited by 1 | Viewed by 1793
Abstract
The adoption and recent development of Unmanned Aerial Vehicles (UAVs) are because of their widespread applications in the private and public sectors, from logistics to environment monitoring. The incorporation of 5G technologies, satellites, and UAVs has provoked telecommunication networks to advance to provide [...] Read more.
The adoption and recent development of Unmanned Aerial Vehicles (UAVs) are because of their widespread applications in the private and public sectors, from logistics to environment monitoring. The incorporation of 5G technologies, satellites, and UAVs has provoked telecommunication networks to advance to provide more stable and high-quality services to remote areas. However, UAVs are vulnerable to cyberattacks because of the rapidly expanding volume and poor inbuilt security. Cyber security and the detection of cyber threats might considerably benefit from the development of artificial intelligence. A machine learning algorithm can be trained to search for attacks that may be similar to other types of attacks. This study proposes a new approach: metaheuristics with machine learning-enabled cybersecurity in unmanned aerial vehicles (MMLCS-UAVs). The presented MMLCS-UAV technique mainly focuses on the recognition and classification of intrusions in the UAV network. To obtain this, the presented MMLCS-UAV technique designed a quantum invasive weed optimization-based feature selection (QIWO-FS) method to select the optimal feature subsets. For intrusion detection, the MMLCS-UAV technique applied a weighted regularized extreme learning machine (WRELM) algorithm with swallow swarm optimization (SSO) as a parameter tuning model. The experimental validation of the MMLCS-UAV method was tested using benchmark datasets. This widespread comparison study reports the superiority of the MMLCS-UAV technique over other existing approaches. Full article
Show Figures

Figure 1

20 pages, 2693 KiB  
Article
STBEAT: Software Update on Trusted Environment Based on ARM TrustZone
by Qi-Xian Huang, Min-Yi Chiu, Chi-Shen Yeh and Hung-Min Sun
Sustainability 2022, 14(20), 13660; https://doi.org/10.3390/su142013660 - 21 Oct 2022
Cited by 1 | Viewed by 1993
Abstract
In recent years, since edge computing has become more and more popular, its security issues have become apparent and have received unprecedented attention. Thus, the current research concentrates on security not only regarding devices such as PCs, smartphones, tablets, and IoTs, but also [...] Read more.
In recent years, since edge computing has become more and more popular, its security issues have become apparent and have received unprecedented attention. Thus, the current research concentrates on security not only regarding devices such as PCs, smartphones, tablets, and IoTs, but also the automobile industry. However, since attack vectors have become more sophisticated than ever, we cannot just protect the zone above the system software layer in a certain operating system, such as Linux, for example. In addition, the challenges in IoT devices, such as power consumption, performance efficiency, and authentication management, still need to be solved. Since most IoT devices are controlled remotely, the security regarding system maintenance and upgrades has become a big issue. Therefore, a mechanism that can maintain IoT devices within a trusted environment based on localhost or over-the-air (OTA) will be a viable solution. We propose a mechanism called STBEAT, integrating an open-source project with ARM TrustZone to solve the challenges of upgrading the IoT system and updating system files more safely. This paper focuses on the ARMv7 architecture and utilizes the security stack from TrustZone to OP-TEE under the STM32 board package, and finally obtains the security key from the trusted application, which is used to conduct the cryptographic operations and then install the newer image on the MMC interface. To sum up, we propose a novel software update strategy and integrated ARM TrustZone security extension to beef up the embedded ecosystem. Full article
Show Figures

Figure 1

14 pages, 4565 KiB  
Article
Refined Information Service Using Knowledge-Base and Deep Learning to Extract Advertisement Articles from Korean Online Articles
by Yongjun Kim, Yung-Cheol Byun and Sang-Joon Lee
Sustainability 2022, 14(20), 13640; https://doi.org/10.3390/su142013640 - 21 Oct 2022
Viewed by 1614
Abstract
We live amidst a flood of information in the internet and digital revolution era. Due to such indiscriminate information access, there are many problems in accurately recognizing the information desired by the user. Moreover, there are many difficulties with finding accurate information and [...] Read more.
We live amidst a flood of information in the internet and digital revolution era. Due to such indiscriminate information access, there are many problems in accurately recognizing the information desired by the user. Moreover, there are many difficulties with finding accurate information and the articles that individuals want due to indiscriminate advertisements in various online papers such as SNS and internet newspapers. Negative experiences with these advertisements lead to advertisement avoidance; if media users avoid advertisements, the media’s existence is threatened. This system aims to provide high-quality online articles, excluding promotions, by designing a system using a knowledge-based management system (KBMS) and Deep Learning system to solve the problems of advertisement. In other words, this system compares advertisement phrases or general keywords related to a specific company and product promotion with the contents to be searched in the database system of the knowledge-based management service. Full article
Show Figures

Figure 1

22 pages, 5650 KiB  
Article
Lightweight Mutual Authentication for Healthcare IoT
by I-Te Chen, Jer-Min Tsai, Yin-Tung Chen and Chung-Hong Lee
Sustainability 2022, 14(20), 13411; https://doi.org/10.3390/su142013411 - 18 Oct 2022
Cited by 3 | Viewed by 1776
Abstract
“Smart medical” applications refer to the fusion of technology and medicine that connects all linked sensor equipment with the patients, including those that measure physiological signals, such as blood pressure, pulse, and ECG. In addition, these physiological signal data are highly private and [...] Read more.
“Smart medical” applications refer to the fusion of technology and medicine that connects all linked sensor equipment with the patients, including those that measure physiological signals, such as blood pressure, pulse, and ECG. In addition, these physiological signal data are highly private and should be safely protected. It takes much longer to complete authentication processes in the traditional way, either based on public key infrastructure or attribute-based encryption, which is a burden for IoT devices. Hence, on the basis of attribute-based encryption, we propose lightweight authentication to shorten the time spent on authentication. Moreover, we use the patients’ data and timestamps as seeds to generate random numbers for authentication. The experiments show that the lightweight authentication using Xeon E3-1230 computer is about 4.45 times faster than complete authentication and 5.8 times faster than complete authentication when using Raspberry Pi. Our proposal significantly improves the disadvantages of IoT devices that lack computing power. Full article
Show Figures

Figure 1

Back to TopTop