Journal of Cybersecurity and Privacy

Due to the wide variety of network services, many different types of protocols exist, producing various packet features. Some features contain irrelevant and redundant information. The presence of such features increases computational complexity and decreases accuracy. Therefore, this research is designed to reduce the data dimensionality and improve the classification accuracy in the UNSW-NB15 dataset. It proposes a hybrid dimensionality reduction system that does feature selection (FS) and feature extraction (FE). FS was performed using the Recursive Feature Elimination (RFE) technique, while FE was accomplished by transforming the features into principal components. This combined scheme reduced a total of 41 input features into 15 components. The proposed systems’ classification performance was determined using an ensemble of Support Vector Classifier (SVC), K-nearest Neighbor classifier (KNC), and Deep Neural Network classifier (DNN). The system was evaluated using accuracy, detection rate, false positive rate, f1-score, and area under the curve metrics. Comparing the voting ensemble results of the full feature set against the 15 principal components confirms that reduced and transformed features did not significantly decrease the classifier’s performance. We achieved 94.34% accuracy, a 93.92% detection rate, a 5.23% false positive rate, a 94.32% f1-score, and a 94.34% area under the curve when 15 components were input to the voting ensemble classifier. Full article

The use of the unindexed web, commonly known as the deep web and dark web, to commit or facilitate criminal activity has drastically increased over the past decade. The dark web is a dangerous place where all kinds of criminal activities take place, Despite advances in web forensic techniques, tools, and methodologies, few studies have formally tackled dark and deep web forensics and the technical differences in terms of investigative techniques and artefact identification and extraction. This study proposes a novel and comprehensive protocol to guide and assist digital forensic professionals in investigating crimes committed on or via the deep and dark web. The protocol, named D2WFP, establishes a new sequential approach for performing investigative activities by observing the order of volatility and implementing a systemic approach covering all browsing-related hives and artefacts which ultimately resulted in improving the accuracy and effectiveness. Rigorous quantitative and qualitative research has been conducted by assessing the D2WFP following a scientifically sound and comprehensive process in different scenarios and the obtained results show an apparent increase in the number of artefacts recovered when adopting the D2WFP which outperforms any current industry or opensource browsing forensic tools. The second contribution of the D2WFP is the robust formulation of artefact correlation and cross-validation within the D2WFP which enables digital forensic professionals to better document and structure their analysis of host-based deep and dark web browsing artefacts. Full article

In the very recent years, cybersecurity attacks have increased at an unprecedented pace, becoming ever more sophisticated and costly. Their impact has involved both private/public companies and critical infrastructures. At the same time, due to the COVID-19 pandemic, the security perimeters of many organizations expanded, causing an increase in the attack surface exploitable by threat actors through malware and phishing attacks. Given these factors, it is of primary importance to monitor the security perimeter and the events occurring in the monitored network, according to a tested security strategy of detection and response. In this paper, we present a protocol tunneling detector prototype which inspects, in near real-time, a company’s network traffic using machine learning techniques. Indeed, tunneling attacks allow malicious actors to maximize the time in which their activity remains undetected. The detector monitors unencrypted network flows and extracts features to detect possible occurring attacks and anomalies by combining machine learning and deep learning. The proposed module can be embedded in any network security monitoring platform able to provide network flow information along with its metadata. The detection capabilities of the implemented prototype have been tested both on benign and malicious datasets. Results show an overall accuracy of $97.1\%$ and an F1-score equal to $95.6\%$. Full article

Cloud-native services face unique cybersecurity challenges due to their distributed infrastructure. They are susceptible to various threats like malware, DDoS attacks, and Man-in-the-Middle (MITM) attacks. Additionally, these services often process sensitive data that must be protected from unauthorized access. On top of that, the dynamic and scalable nature of cloud-native services makes it difficult to maintain consistent security, as deploying new instances and infrastructure introduces new vulnerabilities. To address these challenges, efficient security solutions are needed to mitigate potential threats while aligning with the characteristics of cloud-native services. Despite the abundance of works focusing on security aspects in the cloud, there has been a notable lack of research that is focused on the security of cloud-native services. To address this gap, this work is the first survey that is dedicated to exploring security in cloud-native services. This work aims to provide a comprehensive investigation of the aspects, features, and solutions that are associated with security in cloud-native services. It serves as a uniquely structured mapping study that maps the key aspects to the corresponding features, and these features to numerous contemporary solutions. Furthermore, it includes the identification of various candidate open-source technologies that are capable of supporting the realization of each explored solution. Finally, it showcases how these solutions can work together in order to establish each corresponding feature. The insights and findings of this work can be used by cybersecurity professionals, such as developers and researchers, to enhance the security of cloud-native services. Full article

To address the lack of datasets for agetech, this paper presents an approach for generating synthetic datasets that include traces of benign and attack datasets for agetech. The generated datasets could be used to develop and evaluate intrusion detection systems for smart homes for seniors aging in place. After reviewing several resources, it was established that there are no agetech attack data for sensor readings. Therefore, in this research, several methods for generating attack data were explored using attack data patterns from an existing IoT dataset called TON_IoT weather data. The TON_IoT dataset could be used in different scenarios, but in this study, the focus is to apply it to agetech. The attack patterns were replicated in a normal agetech dataset from a temperature sensor collected from the Information Security and Object Technology (ISOT) research lab. The generated data are different from normal data, as abnormal segments are shown that could be considered as attacks. The generated agetech attack datasets were also trained using machine learning models, and, based on different metrics, achieved good classification performance in predicting whether a sample is benign or malicious. Full article

Training-anomaly-based, machine-learning-based, intrusion detection systems (AMiDS) for use in critical Internet of Things (CioT) systems and military Internet of Things (MioT) environments may involve synthetic data or publicly simulated data due to data restrictions, data scarcity, or both. However, synthetic data can be unrealistic and potentially biased, and simulated data are invariably static, unrealistic, and prone to obsolescence. Building an AMiDS logical model to predict the deviation from normal behavior in MioT and CioT devices operating at the sensing or perception layer due to adversarial attacks often requires the model to be trained using current and realistic data. Unfortunately, while real-time data are realistic and relevant, they are largely imbalanced. Imbalanced data have a skewed class distribution and low-similarity index, thus hindering the model’s ability to recognize important features in the dataset and make accurate predictions. Data-driven learning using data sampling, resampling, and generative methods can lessen the adverse impact of a data imbalance on the AMiDS model’s performance and prediction accuracy. Generative methods enable passive adversarial learning. This paper investigates several data sampling, resampling, and generative methods. It examines their impacts on the performance and prediction accuracy of AMiDS models trained using imbalanced data drawn from the UNSW_2018_IoT_Botnet dataset, a publicly available IoT dataset from the IEEEDataPort. Furthermore, it evaluates the performance and predictability of these models when trained using data transformation methods, such as normalization and one-hot encoding, to cover a skewed distribution, data sampling and resampling methods to address data imbalances, and generative methods to train the models to increase the model’s robustness to recognize new but similar attacks. In this initial study, we focus on CioT systems and train PCA-based and oSVM-based AMiDS models constructed using low-complexity PCA and one-class SVM (oSVM) ML algorithms to fit an imbalanced ground truth IoT dataset. Overall, we consider the rare event prediction case where the minority class distribution is disproportionately low compared to the majority class distribution. We plan to use transfer learning in future studies to generalize our initial findings to the MioT environment. We focus on CioT systems and MioT environments instead of traditional or non-critical IoT environments due to the stringent low energy, the minimal response time constraints, and the variety of low-power, situational-aware (or both) things operating at the sensing or perception layer in a highly complex and open environment. Full article

Smart grids have emerged as a transformative technology in the power sector, enabling efficient energy management. However, the increased reliance on digital technologies also exposes smart grids to various cybersecurity threats and attacks. This article provides a comprehensive exploration of cyberattacks and cybersecurity in smart grids, focusing on critical components and applications. It examines various cyberattack types and their implications on smart grids, backed by real-world case studies and quantitative models. To select optimal cybersecurity options, the study proposes a multi-criteria decision-making (MCDM) approach using the analytical hierarchy process (AHP). Additionally, the integration of artificial intelligence (AI) techniques in smart-grid security is examined, highlighting the potential benefits and challenges. Overall, the findings suggest that “security effectiveness” holds the highest importance, followed by “cost-effectiveness”, “scalability”, and “Integration and compatibility”, while other criteria (i.e., “performance impact”, “manageability and usability”, “compliance and regulatory requirements”, “resilience and redundancy”, “vendor support and collaboration”, and “future readiness”) contribute to the evaluation but have relatively lower weights. Alternatives such as “access control and authentication” and “security information and event management” with high weighted sums are crucial for enhancing cybersecurity in smart grids, while alternatives such as “compliance and regulatory requirements” and “encryption” have lower weighted sums but still provide value in their respective criteria. We also find that “deep learning” emerges as the most effective AI technique for enhancing cybersecurity in smart grids, followed by “hybrid approaches”, “Bayesian networks”, “swarm intelligence”, and “machine learning”, while “fuzzy logic”, “natural language processing”, “expert systems”, and “genetic algorithms” exhibit lower effectiveness in addressing smart-grid cybersecurity. The article discusses the benefits and drawbacks of MCDM-AHP, proposes enhancements for its use in smart-grid cybersecurity, and suggests exploring alternative MCDM techniques for evaluating security options in smart grids. The approach aids decision-makers in the smart-grid field to make informed cybersecurity choices and optimize resource allocation. Full article

Anonymization techniques are widely used to make personal data broadly available for analytics/data-mining purposes while preserving the privacy of the personal information enclosed in it. In the past decades, a substantial number of anonymization techniques were developed based on the famous four privacy models such as k-anonymity, ℓ-diversity, t-closeness, and differential privacy. In recent years, there has been an increasing focus on developing attribute-centric anonymization methods, i.e., methods that exploit the properties of the underlying data to be anonymized to improve privacy, utility, and/or computing overheads. In addition, synthetic data are also widely used to preserve privacy (privacy-enhancing technologies), as well as to meet the growing demand for data. To the best of the authors’ knowledge, none of the previous studies have covered the distinctive features of attribute-centric anonymization methods and synthetic data based developments. To cover this research gap, this paper summarizes the recent state-of-the-art (SOTA) attribute-centric anonymization methods and synthetic data based developments, along with the experimental details. We report various innovative privacy-enhancing technologies that are used to protect the privacy of personal data enclosed in various forms. We discuss the challenges and the way forward in this line of work to effectively preserve both utility and privacy. This is the first work that systematically covers the recent development in attribute-centric and synthetic-data-based privacy-preserving methods and provides a broader overview of the recent developments in the privacy domain. Full article

Business Email Compromise (BEC) attacks have emerged as serious threats to organizations in recent years, exploiting social engineering and malware to dupe victims into divulging confidential information and executing fraudulent transactions. This paper provides a comprehensive review of BEC attacks, including their principles, techniques, and impacts on enterprises. In light of the rising tide of BEC attacks globally and their significant financial impact on business, it is crucial to understand their modus operandi and adopt proactive measures to protect sensitive information and prevent financial losses. This study offers valuable recommendations and insights for organizations seeking to enhance their cybersecurity posture and mitigate the risks associated with BEC attacks. Moreover, we analyze the Greek landscape of cyberattacks, focusing on the existing regulatory framework and the measures taken to prevent and respond to cybercrime in accordance with the NIS Directives of the EU. By examining the Greek landscape, we gain insights into the effectiveness of countermeasures in this region, as well as the challenges and opportunities for improving cybersecurity practices. Full article

Cooperative Intelligent Transport Systems (C-ITSs) are an important development for society. C-ITSs enhance road safety, improve traffic efficiency, and promote sustainable transportation through interconnected and intelligent communication between vehicles, infrastructure, and traffic-management systems. Many real-world implementations still consider traditional Public Key Infrastructures (PKI) as the underlying trust model and security control. However, there are challenges with the PKI-based security control from a scalability and revocation perspective. Lately, certificateless cryptography has gained research attention, also in conjunction with C-ITSs, making it a new type of security control to be considered. In this study, we use certificateless cryptography as a candidate to investigate factors affecting decisions (not) to adopt new types of security controls, and study its current gaps, key challenges and possible enablers which can influence the industry. We provide a qualitative study with industry specialists in C-ITSs, combined with a literature analysis of the current state of research in certificateless cryptographic in C-ITS. It was found that only 53% of the current certificateless cryptography literature for C-ITSs in 2022–2023 provide laboratory testing of the protocols, and 0% have testing in real-world settings. However, the trend of research output in the field has been increasing linearly since 2016 with more than eight times as many articles in 2022 compared to 2016. Based on our analysis, using a five-phased Innovation-Decision Model, we found that key reasons affecting adoption are: availability of proof-of-concepts, knowledge beyond current best practices, and a strong buy-in from both stakeholders and standardization bodies. Full article

The widespread adoption of cloud-based and public legitimate services (CPLS) has inadvertently opened up new avenues for cyber attackers to establish covert and resilient command-and-control (C&C) communication channels. This abuse poses a significant cybersecurity threat, as it allows malicious traffic to blend seamlessly with legitimate network activities. Traditional detection systems are proving inadequate in accurately identifying such abuses, emphasizing the urgent need for more advanced detection techniques. In our study, we conducted an extensive systematic literature review (SLR) encompassing the academic and industrial literature from 2008 to July 2023. Our review provides a comprehensive categorization of the attack techniques employed in CPLS abuses and offers a detailed overview of the currently developed detection strategies. Our findings indicate a substantial increase in cloud-based abuses, facilitated by various attack techniques. Despite this alarming trend, the focus on developing detection strategies remains limited, with only 7 out of 91 studies addressing this concern. Our research serves as a comprehensive review of CPLS abuse for the C&C infrastructure. By examining the emerging techniques used in these attacks, we aim to make a significant contribution to the development of effective botnet defense strategies. Full article

An intrusion detection system (IDS), whether as a device or software-based agent, plays a significant role in networks and systems security by continuously monitoring traffic behaviour to detect malicious activities. The literature includes IDSs that leverage models trained to detect known attack behaviours. However, such models suffer from low accuracy or high overfitting. This work aims to enhance the performance of the IDS by making a model based on the observed traffic via applying different single and ensemble classifiers and lowering the classifier’s overfitting on a reduced set of features. We implement various feature reduction techniques, including Linear Regression, LASSO, Random Forest, Boruta, and autoencoders on the CSE-CIC-IDS2018 dataset to provide a training set for classifiers, including Decision Tree, Naïve Bayes, neural networks, Random Forest, and XGBoost. Our experiments show that the Decision Tree classifier on autoencoders-based reduced sets of features yields the lowest overfitting among other combinations. Full article

Autonomous vehicles (AVs), defined as vehicles capable of navigation and decision-making independent of human intervention, represent a revolutionary advancement in transportation technology. These vehicles operate by synthesizing an array of sophisticated technologies, including sensors, cameras, GPS, radar, light imaging detection and ranging (LiDAR), and advanced computing systems. These components work in concert to accurately perceive the vehicle’s environment, ensuring the capacity to make optimal decisions in real-time. At the heart of AV functionality lies the ability to facilitate intercommunication between vehicles and with critical road infrastructure—a characteristic that, while central to their efficacy, also renders them susceptible to cyber threats. The potential infiltration of these communication channels poses a severe threat, enabling the possibility of personal information theft or the introduction of malicious software that could compromise vehicle safety. This paper offers a comprehensive exploration of the current state of AV technology, particularly examining the intersection of autonomous vehicles and emotional intelligence. We delve into an extensive analysis of recent research on safety lapses and security vulnerabilities in autonomous vehicles, placing specific emphasis on the different types of cyber attacks to which they are susceptible. We further explore the various security solutions that have been proposed and implemented to address these threats. The discussion not only provides an overview of the existing challenges but also presents a pathway toward future research directions. This includes potential advancements in the AV field, the continued refinement of safety measures, and the development of more robust, resilient security mechanisms. Ultimately, this paper seeks to contribute to a deeper understanding of the safety and security landscape of autonomous vehicles, fostering discourse on the intricate balance between technological advancement and security in this rapidly evolving field. Full article

Network emulation offers a flexible solution for network deployment and operations, leveraging software to consolidate all nodes in a topology and utilizing the resources of a single host system server. This research paper investigated the state of cybersecurity in virtualized systems, covering vulnerabilities, exploitation techniques, remediation methods, and deployment strategies, based on an extensive review of the related literature. We conducted a comprehensive performance evaluation and comparison of two network-emulation platforms: Graphical Network Simulator-3 (GNS3), an established open-source platform, and the SEED Internet Emulator, an emerging platform, alongside physical Cisco routers. Additionally, we present a Distributed System that seamlessly integrates network architecture and emulation capabilities. Empirical experiments assessed various performance criteria, including the bandwidth, throughput, latency, and jitter. Insights into the advantages, challenges, and limitations of each platform are provided based on the performance evaluation. Furthermore, we analyzed the deployment costs and energy consumption, focusing on the economic aspects of the proposed application. Full article

With the growth in network usage, there has been a corresponding growth in the nefarious exploitation of this technology. A wide array of techniques is now available that can be used to deal with cyberattacks, and one of them is network intrusion detection. Artificial Intelligence (AI) and Machine Learning (ML) techniques have extensively been employed to identify network anomalies. This paper provides an effective technique to evaluate the classification performance of a deep-learning-based Feedforward Neural Network (FFNN) classifier. A small feature vector is used to detect network traffic anomalies in the UNSW-NB15 and NSL-KDD datasets. The results show that a large feature set can have redundant and unuseful features, and it requires high computation power. The proposed technique exploits a small feature vector and achieves better classification accuracy. Full article

Network anomaly detection solutions can analyze a network’s data volume by protocol over time and can detect many kinds of cyberattacks such as exfiltration. We use exponential random graph models (ERGMs) in order to flatten hourly network topological characteristics into a time series, and Autoregressive Moving Average (ARMA) to analyze that time series and to detect potential attacks. In particular, we extend our previous method in not only demonstrating detection over hourly data but also through labeling of nodes and over the HTTP protocol. We demonstrate the effectiveness of our method using real-world data for creating exfiltration scenarios. We highlight how our method has the potential to provide a useful description of what is happening in the network structure and how this can assist cybersecurity analysts in making better decisions in conjunction with existing intrusion detection systems. Finally, we describe some strengths of our method, its accuracy based on the right selection of parameters, as well as its low computational requirements. Full article

Message Queue Telemetry Transport (MQTT) is a common communication protocol used in the Internet of Things (IoT). MQTT is a simple, lightweight messaging protocol used to establish communication between multiple devices relying on the publish–subscribe model. However, the protocol does not provide authentication, and most proposals to incorporate it lose their lightweight feature and do not consider the future risk of quantum attacks. IoT devices are generally resource-constrained, and postquantum cryptography is often more computationally resource-intensive compared to current cryptographic standards, adding to the complexity of the transition. In this paper, we use the postquantum digital signature scheme CRYSTALS-Dilithium to provide authentication for MQTT and determine what the CPU, memory and disk usage are when doing so. We further investigate another possibility to provide authentication when using MQTT, namely a key encapsulation mechanism (KEM) trick proposed in 2020 for transport level security (TLS). Such a trick is claimed to save up to 90% in CPU cycles. We use the postquantum KEM scheme CRYSTALS-KYBER and compare the resulting CPU, memory and disk usages with traditional authentication. We found that the use of KEM for authentication resulted in a speed increase of 25 ms, a saving of 71%. There were some extra costs for memory but this is minimal enough to be acceptable for most IoT devices. Full article

Several studies have shown that the traditional way of learning is not optimal when we aim to improve ICT users’ actual privacy behaviors. In this research, we present a literature review of the theories that are followed in other fields to modify human behavior. Our findings show that cognitive theory and the health belief model present optimistic results. Further, we examined various learning methods, and we concluded that experiential learning is advantageous compared to other methods. In this paper, we aggregate the privacy behavior determinant factors found in the literature and use cognitive theory to synthesize a theoretical framework. The proposed framework can be beneficial to educational policymakers and practitioners in institutions such as public and private schools and universities. Also, our framework provides a fertile ground for more research on experiential privacy learning and privacy behavior enhancement. Full article

The ubiquity of Android smartphones makes them targets of sophisticated malware, which maintain long-term stealth, particularly by offloading attack steps to benign apps. Such malware leaves little to no trace in logs, and the attack steps become difficult to discern from benign app functionality. Endpoint detection and response (EDR) systems provide live forensic capabilities that enable anomaly detection techniques to detect anomalous behavior in application logs after an app hijack. However, this presents a challenge, as state-of-the-art EDRs rely on device and third-party application logs, which may not include evidence of attack steps, thus prohibiting anomaly detection techniques from exposing anomalous behavior. While, theoretically, all the evidence resides in volatile memory, its ephemerality necessitates timely collection, and its extraction requires device rooting or app repackaging. We present VEDRANDO, an enhanced EDR for Android that accomplishes (i) the challenge of timely collection of volatile memory artefacts and (ii) the detection of a class of stealthy attacks that hijack benign applications. VEDRANDO leverages memory forensics and app virtualization techniques to collect timely evidence from memory, which allows uncovering attack steps currently uncollected by the state-of-the-art EDRs. The results showed that, with less than 5% CPU overhead compared to normal usage, VEDRANDO could uniquely collect and fully reconstruct the stealthy attack steps of ten realistic messaging hijack attacks using standard anomaly detection techniques, without requiring device or app modification. Full article