Developing Resilient Cyber-Physical Systems: A Review of State-of-the-Art Malware Detection Approaches, Gaps, and Future Directions

Abstract

Cyber-physical systems (CPSes) are rapidly evolving in critical infrastructure (CI) domains such as smart grid, healthcare, the military, and telecommunication. These systems are continually threatened by malicious software (malware) attacks by adversaries due to their improvised tactics and attack methods. A minor configuration change in a CPS through malware has devastating effects, which the world has seen in Stuxnet, BlackEnergy, Industroyer, and Triton. This paper is a comprehensive review of malware analysis practices currently being used and their limitations and efficacy in securing CPSes. Using well-known real-world incidents, we have covered the significant impacts when a CPS is compromised. In particular, we have prepared exhaustive hypothetical scenarios to discuss the implications of false positives on CPSes. To improve the security of critical systems, we believe that nature-inspired metaheuristic algorithms can effectively counter the overwhelming malware threats geared toward CPSes. However, our detailed review shows that these algorithms have not been adapted to their full potential to counter malicious software. Finally, the gaps identified through this research have led us to propose future research directions using nature-inspired algorithms that would help in bringing optimization by reducing false positives, thereby increasing the security of such systems.

Examining Windows File System IRP Operations with Machine Learning for Ransomware Detection

“…Furthermore, sandboxing environments were extensively studied for their effectiveness in isolating and analyzing ransomware behavior, although their evasion by advanced ransomware poses significant challenges [26], [27]. The development of heuristic-based algorithms demonstrated potential in adapting to evolving ransomware variants, yet their reliance on predefined rules could be circumvented by sophisticated attacks [28], [29]. Lastly, the significance of incorporating threat intelligence platforms for real-time ransomware analysis and prediction was underscored, highlighting the importance of a multifaceted approach to ransomware detection [30], [31].…”

Deep learning-powered malware detection in cyberspace: a contemporary review

“…Furthermore, the interpretability of models remains a critical concern, impeding the deployment of reliable and understandable solutions. When it comes to Cyber-Physical System (CPS) malware detection, the complexity of different malware classes and their numerous variants ma kes detection even more challenging [7]. The rise of Advanced Persistent Threats (APTs) adds another layer of sophistication, demanding advanced strategies to combat coordinated and purposeful attacks.…”

“…Behavioural analysis, while effective, faces scalability issues and might overlook subtle anomalies. Non-deep learning machine learning algorithms such as Decision Trees and SVMs demand expert feature engineering and struggle with high-dimensional data complexity [7].…”

An Accurate Metaheuristic Mountain Gazelle Optimizer for Parameter Estimation of Single- and Double-Diode Photovoltaic Cell Models

“…Currently, metaheuristic algorithms seen a substantial history to achieve the optimal solution in fine-tuning machine learning algorithms and solving continuous optimization problems [27,28]. They have gained great popularity in different application domains such as smart grid applications [29][30][31], Green Building Energy-Optimization Systems (GBEOSs) [32], Electric Vehicles (EVs) [33][34][35], the Internet of Things (IoT) [36][37][38][39], the military domain [40][41][42], structural health monitoring applications [43,44], Resilient Cyber-Physical Systems (RCPSs) [45,46], robotics [47,48], etc. With the growth of solar energy systems and their various design and control aspects seen as complex problems, where metaheuristics are the best candidates for addressing them, PV cell parameter identification is becoming a wide research discipline, which involves artificial intelligence and bio-inspired optimization algorithms.…”