Computers & Security is the most respected technical journal in the IT security field. Now in its 29th year, with a new editorial board and new regular features and columns, the journal is essential reading for IT security professionals around the world.

Computers & Security provides you with a unique blend of leading edge research and sound practical management advice. It is aimed at the professional involved with computer security, audit, control and data integrity in all sectors - industry, commerce and academia. Recognized worldwide as THE primary source of reference for applied research and technical expertise it is your first step to fully secure systems.

Subscribe today and see the benefits immediately!

• Our cutting edge research will help you secure and maintain the integrity of your systems
• We accept only the highest quality of papers ensuring that you receive the relevant and practical advice you need
• Our editorial board's collective expertise will save you from paying thousands of pounds to IT consultants
• We don't just highlight the threats, we give you the solutions

Special Issue on Anomaly Detection in Cyber-Physical Systems
Submission Date: 2023-08-15

Rapid changes in the digital technologies landscape have been significantly transforming industrial processes, due to the deep integration between physical and digital components of production environments, leading to the development of the so-called Cyber-Physical Systems (CPS). The application of data analytics techniques to CPSs has shown incredible potential in a variety of domains: maintenance cost reduction, machine fault reduction, repair downtime reduction, spare parts inventory reduction, increased spare part life, increased overall production, improvement in operator safety, repair verification, and overall profit. However, while machine learning and deep learning approaches are promising due to their accurate predictive abilities, their data-heavy requirements make them significantly limited in real-world applications (see [1] for more details).

In recent years, several anomaly detection methods have been proposed in different domains, but traditional approaches cannot be directly applied to ensure the security of CPSs due to their increasing complexity and more sophisticated attacks [2]. In particular, these methods can be challenged by the growing volume of data and need domain-specific knowledge, which requires innovative solutions integrating advanced artificial intelligence models together with different sources of information (e.g., measurements from IoT sensors,
topology and network information).

Nevertheless, the recent rise in cyber-physical attacks (e.g., Triton and Stuxnet), which can deceive monitoring platforms, poses novel and challenging issues [3,4]. For this reason, advanced predictive maintenance techniques are starting to exploit different features of specific industrial equipment that can be analyzed to unveil symptoms of possible failures, include those caused by malicious activity [5].

In summary, the objective of this special issue is to investigate, analyze and address challenging issues and emerging trends [6,7] in Anomaly Detection for Cyber-Physical Systems. To this aim, we solicit contributions on advanced modeling and mining of Anomaly Detection for Cyber-Physical System, including both theoretical and application-oriented studies promoting and building explainable AI models. In particular, we encourage contributions on the development of novel approaches based on advanced optimization techniques and learning paradigms (e.g., online learning, reinforcement learning, and deep learning) to enhance our understanding of complex phenomena in Cyber-Physical System.

The topics of interest for this special issue include but are not limited to:

(i) Supervised, Semi-supervised and unsupervised techniques for anomaly detection in CPS;
(ii) Representation learning, Transfer learning, Sequence learning and Reinforcement learning based methods for anomaly detection in CPS;
(iii) Explainable Artificial Intelligence techniques for anomaly detection in CPS;
(iv) Game theory and Adversarial learning approach for anomaly detection in CPS;
(v) Federated learning for anomaly detection in CPS;
(vi) Multi-dataset time series for anomaly detection in CPS;
(vii) Multi-dataset Time Series Anomaly Detection.