Authors | Q. Xu, S. Ali and T. Yue |
Title | Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems |
Afilliation | Software Engineering |
Project(s) | Department of Engineering Complex Software Systems, Co-tester: Collective-Adaptive Testing of Coevolving Autonomous Cyber-Physical Systems of Systems under Uncertainty, Digital Twin-Enabled Operation Time Analyses, Design-Operation Continuum Methods for Testing and Deployment under Unforeseen Conditions for Cyber-Physical Systems of Systems |
Status | Accepted |
Publication Type | Journal Article |
Year of Publication | 2023 |
Journal | ACM Transactions on Software Engineering and Methodology |
Publisher | ACM |
Place Published | TOSEM |
Abstract | Anomaly detection is critical to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of attacks and CPS themselves, anomaly detection in CPS is becoming more and more challenging. In our previous work, we proposed a digital twin-based anomaly detection method, called ATTAIN, which takes advantage of both historical and real-time data of CPS. However, such data vary significantly in terms of difficulty. Therefore, similar to human learning processes, deep learning models (e.g., ATTAIN) can benefit from an easy-to-difficult curriculum. To this end, in this paper, we present a novel approach, named |
Citation Key | 43107 |