JESTIE Special Section on “Enhancing Safety and Security in Industrial Cyber-Physical Systems through Machine Learning”
Organized by: Dong Zhao, Ahmad Al-Dabbagh, Changsheng Hua, Yang Shi
The rapid advancement of computation, communication, control, and sensing technologies has led to the emergence of industrial cyber-physical systems. As industrial cyber-physical systems continue to demonstrate their prowess in daily life, ensuring their safety and security has risen to the forefront of concern. The inherent susceptibility of industrial cyber-physical systems to cyber threats underscores the criticality of addressing potential risks such as cyber attacks and privacy breaches. Furthermore, as these systems expand in scale and complexity, the emergence of faults poses a distinct threat to functional safety. Thus, the need to meticulously address both safety and security challenges confronting industrial cyber-physical systems is irrefutable. Machine learning theories and technologies have garnered substantial acclaim and success. Applying these machine learning methods to tackle safety and security issues in industrial cyber-physical systems holds great promise. This special issue is dedicated to advancing machine learning theories and technologies that address safety and security issues within industrial cyber-physical systems, presenting novel contributions in both theoretical foundations and practical designs.
Papers with implementations, applications in industry, and experimental results are welcome. Topics encompassed within this issue span, but are not confined to, the following areas:
- Machine learning-based process monitoring and fault diagnosis for industrial cyber-physical systems
- Machine learning techniques for detecting cyber attacks on industrial cyber-physical systems
- Design of cyber attacks on industrial cyber-physical systems informed by machine learning methods
- Integration of machine learning-based defense, detection, or mitigation strategies for industrial cyberphysical systems facing attacks or faults
- Fault-tolerant control of industrial cyber-physical systems through machine learning methods
- Resilient control and estimation of industrial cyberphysical systems via machine learning strategies
- Privacy-preserving methodologies in industrial cyberphysical systems facilitated by machine learning methods
- Secure applications of machine learning in industrial cyber-physical systems