Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning

TL;DR

This paper proposes a novel approach using Deep Reinforcement Learning to efficiently falsify cyber-physical systems by reducing the number of simulations needed to find counterexamples, addressing practical limitations of existing methods.

Contribution

It introduces a DRL-based method for CPS falsification that significantly decreases simulation runs compared to traditional optimization techniques.

Findings

DRL reduces the number of simulations needed for falsification.

Preliminary results show promising effectiveness of the approach.

Method improves efficiency over existing techniques.

Abstract

With the rapid development of software and distributed computing, Cyber-Physical Systems (CPS) are widely adopted in many application areas, e.g., smart grid, autonomous automobile. It is difficult to detect defects in CPS models due to the complexities involved in the software and physical systems. To find defects in CPS models efficiently, robustness guided falsification of CPS is introduced. Existing methods use several optimization techniques to generate counterexamples, which falsify the given properties of a CPS. However those methods may require a large number of simulation runs to find the counterexample and is far from practical. In this work, we explore state-of-the-art Deep Reinforcement Learning (DRL) techniques to reduce the number of simulation runs required to find such counterexamples. We report our method and the preliminary evaluation results.