Learning-Based Vulnerability Analysis of Cyber-Physical Systems

TL;DR

This paper introduces a learning-based approach to generate stealthy sensor attacks on cyber-physical systems, aiming to assess their vulnerability by maximizing system disruption while evading detection.

Contribution

It develops a novel grey-box framework with neural network models trained to produce real-time, effective sensor attacks, enhancing vulnerability analysis of CPS.

Findings

Proposed attack models successfully degrade system performance in case studies.

Models generate stealthy attacks that evade anomaly detection.

Framework enables real-time attack generation based on learned patterns.

Abstract

This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS). Specifically, we consider a control architecture widely used in CPS (e.g., robotics), where the low-level control is based on e.g., the extended Kalman filter (EKF) and an anomaly detector. To facilitate analyzing the impact potential sensing attacks could have, our objective is to develop learning-enabled attack generators capable of designing stealthy attacks that maximally degrade system operation. We show how such problem can be cast within a learning-based grey-box framework where parts of the runtime information are known to the attacker, and introduce two models based on feed-forward neural networks (FNN); both models are trained offline, using a cost function that combines the attack effects on the estimation error and the residual signal used for anomaly detection, so that the trained models are capable of recursively generating such effective sensor attacks in real-time. The effectiveness of the proposed methods is illustrated on several case studies.