Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems
This addresses safety and security issues in cyber-physical systems like medical devices, but it is incremental as it applies existing robustness testing methods to a new domain.
The paper tackled the problem of low robustness in machine learning-based anomaly detection for cyber-physical systems against accidental and malicious perturbations, finding that integrating domain knowledge reduced robustness error by up to 54.2% while maintaining high F1 scores and transparency in artificial pancreas system case studies.
The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models often suffer from low performance in predicting unexpected data and are vulnerable to accidental or malicious perturbations. Although robustness testing of deep learning models has been extensively explored in applications such as image classification and speech recognition, less attention has been paid to ML-driven safety monitoring in CPS. This paper presents the preliminary results on evaluating the robustness of ML-based anomaly detection methods in safety-critical CPS against two types of accidental and malicious input perturbations, generated using a Gaussian-based noise model and the Fast Gradient Sign Method (FGSM). We test the hypothesis of whether integrating the domain knowledge (e.g., on unsafe system behavior) with the ML models can improve the robustness of anomaly detection without sacrificing accuracy and transparency. Experimental results with two case studies of Artificial Pancreas Systems (APS) for diabetes management show that ML-based safety monitors trained with domain knowledge can reduce on average up to 54.2% of robustness error and keep the average F1 scores high while improving transparency.