The security of safety-critical IoT systems, such as the Internet of Vehicles (IoV), has a great interest, focusing on using Intrusion Detection Systems (IDS) to recognise cyber-attacks in IoT networks. Deep learning methods are commonly used for the anomaly detection engines of many IDSs because of their ability to learn from heterogeneous data. However, while this type of machine learning model produces high false-positive rates and the reasons behind its predictions are not easily understood, even by experts. The ability to understand or comprehend the reasoning behind the decision of an IDS to block a particular packet helps cybersecurity experts validate the system’s effectiveness and develop more cyber-resilient systems. This paper proposes an explainable deep learning-based intrusion detection framework that helps improve the transparency and resiliency of DL-based IDS in IoT networks. The framework employs a SHapley Additive exPlanations (SHAP) mechanism to interpret decisions made by deep learning-based IDS to experts who rely on the decisions to ensure IoT networks’ security and design more cyber-resilient systems. The proposed framework was validated using the ToN_IoT dataset and compared with other compelling techniques. The experimental results have revealed the high performance of the proposed framework with a 99.15% accuracy and a 98.83% F1 score, illustrating its capability to protect IoV networks against sophisticated cyber-attacks.

The prevalence of interconnected appliances and ubiquitous computing face serious threats from the hostile activities of network attackers. Conventional Intrusion Detection Systems (IDSs) are incapable of detecting these intrusive events as their outcomes reflect high false positive rates (FPRs). In this paper, we present a novel Geometric Area Analysis (GAA) technique based on Trapezoidal Area Estimation (TAE) for each observation computed from the parameters of the Beta Mixture Model (BMM) for features and the distances between observations. As this GAA-based detection depends on the methodology of anomaly-based detection (ADS), it constructs the areas of normal observations in a normal profile with those of the testing set estimated from the same parameters to recognise abnormal patterns. We also design a scalable framework for handling large-scale networks, and our GAA technique considers a decision engine module in this framework. The performance of our GAA technique is evaluated using the NSL-KDD and UNSW-NB15 datasets. To reduce the high-dimensional data of network connections, we apply the Principal Component Analysis (PCA) and evaluate its influence on the GAA technique. The empirical results show that our technique achieves a higher detection rate and lower FPR with a lower processing time than other competing methods.

Firmware-based malware is an emerging threat with few obvious mechanisms for detection. There have been multiple cases where the presence of firmware-based malware has been confirmed or strongly suspected, and current mitigations strategies have little or no recourse. Volatile memory forensics may be one of the few technologies that can be employed to detect the presence of modified firmware, through ROM shadowing. However, the majority of volatile memory forensic tools were not designed with this use-case in mind and may not be suited to the capture of protected memory regions. This work performs experimental analysis to determine which, if any, memory acquisition tools are able to collect evidence pertaining to firmware-based rootkits or malware.

Host-based anomaly intrusion detection system design is very challenging due to the notoriously high false alarm rate. This paper introduces a new host-based anomaly intrusion detection methodology using discontiguous system call patterns, in an attempt to increase detection rates whilst reducing false alarm rates. The key concept is to apply a semantic structure to kernel level system calls in order to reflect intrinsic activities hidden in high-level programming languages, which can help understand program anomaly behaviour. Excellent results were demonstrated using a variety of decision engines, evaluating the KDD98 and UNM data sets, and a new, modern data set. The ADFA Linux data set was created as part of this research using a modern operating system and contemporary hacking methods, and is now publicly available. Furthermore, the new semantic method possesses an inherent resilience to mimicry attacks, and demonstrated a high level of portability between different operating system versions.

Intrusion detection systems are generally tested using datasets compiled at the end of last century, justified by the need for publicly available test data and the lack of any other alternative datasets. Prominent amongst this legacy group is the KDD project. Whilst a seminal contribution at the time of compilation, these datasets no longer represent relevant architecture or contemporary attack protocols, and are beset by data corruptions and inconsistencies. Hence, testing of new IDS approaches against these datasets does not provide an effective performance metric, and contributes to erroneous efficacy claims. This paper introduces a new publicly available dataset which is representative of modern attack structure and methodology. The new dataset is contrasted with the legacy datasets, and the performance difference of commonly used intrusion detection algorithms is highlighted.