Anomaly Detection
Learning-based attack detection and localization
Approach
Approach 1: Guassian Process Regression-based deetctor
For each measurement node, a data-driven auxiliary measurement prior is constructed based on a generative probabilistic regression model constructed using Gaussian process (GP).
Approach 2: MLP Classifier-based deetctor
An example
Adversarial Training
Relevant paper
- [Book chapter] Y. Zheng, and Olugbenga Moses Anubi “Resilient Observer Design for Cyber-Physical Systems with Data-Driven Measurement Pruning ”, Security and Resilience in Cyber-Physical Systems, Edited by Ali Zemouche and Masoud Abbaszadeh, Springer. (2022)
- Y. Zheng, Ali Sayghe, OM Anubi, “Algorithm Design for Resilient Cyber-Physical Systems using an Automated Attack Generative Model”, IEEE Transactions on Cyber-Physical Systems. [Under review], (2023).