Data-Driven Falsification of Cyber-Physical Systems
Atanu Kundu, Sauvik Gon, Rajarshi Ray
TL;DR
This work tackles falsification of safety properties in Cyber-Physical Systems by proposing FlexiFal, a data-driven framework that builds surrogate models of the CPS either as a deep neural network or a decision tree. The CPS-to-surrogate mapping enables the use of DNN falsification tools and, alternatively, a decision-tree guided approach that leverages explanations to efficiently generate counterexamples. Empirical results on CPS benchmarks (including ARCH-COMP 2024) show that the decision-tree grounded method (DTFal) often finds multiple hard-to-find counterexamples more efficiently, while the DNN-based route (NNFal) plus verification offers complementary capabilities. The framework provides practical value by rapidly identifying unsafe trajectories, sparing detailed full CPS verification, and by releasing datasets and surrogate models to the community for further research.
Abstract
Cyber-Physical Systems (CPS) are abundant in safety-critical domains such as healthcare, avionics, and autonomous vehicles. Formal verification of their operational safety is, therefore, of utmost importance. In this paper, we address the falsification problem, where the focus is on searching for an unsafe execution in the system instead of proving their absence. The contribution of this paper is a framework that (a) connects the falsification of CPS with the falsification of deep neural networks (DNNs) and (b) leverages the inherent interpretability of Decision Trees for faster falsification of CPS. This is achieved by: (1) building a surrogate model of the CPS under test, either as a DNN model or a Decision Tree, (2) application of various DNN falsification tools to falsify CPS, and (3) a novel falsification algorithm guided by the explanations of safety violations of the CPS model extracted from its Decision Tree surrogate. The proposed framework has the potential to exploit a repertoire of \emph{adversarial attack} algorithms designed to falsify robustness properties of DNNs, as well as state-of-the-art falsification algorithms for DNNs. Although the presented methodology is applicable to systems that can be executed/simulated in general, we demonstrate its effectiveness, particularly in CPS. We show that our framework, implemented as a tool \textsc{FlexiFal}, can detect hard-to-find counterexamples in CPS that have linear and non-linear dynamics. Decision tree-guided falsification shows promising results in efficiently finding multiple counterexamples in the ARCH-COMP 2024 falsification benchmarks~\cite{khandait2024arch}.