# Data-Driven Falsification of Cyber-Physical Systems

arXiv: https://arxiv.org/abs/2505.03863 · HTML: https://mlsanity.com/paper/2505.03863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Efficient Formal Safety Analysis of Neural Networks](https://mlsanity.com/paper/1809.08098/) (2018)
- [Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses](https://mlsanity.com/paper/1811.09600/) (2018)
- [DNNV: A Framework for Deep Neural Network Verification](https://mlsanity.com/paper/2105.12841/) (2021)
- [DRYVR:Data-driven verification and compositional reasoning for automotive systems](https://mlsanity.com/paper/1702.06902/) (2017)
- [Gray-box Adversarial Testing for Control Systems with Machine Learning Component](https://mlsanity.com/paper/1812.11958/) (2018)
- [Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: An Approach Based on System Identification](https://mlsanity.com/paper/1910.02837/) (2019)
- [Falsification of Cyber-Physical Systems with Robustness-Guided Black-Box Checking](https://mlsanity.com/paper/2005.02126/) (2020)
- [Online GANs for Automatic Performance Testing](https://mlsanity.com/paper/2104.11069/) (2021)
- [PSY-TaLiRo: A Python Toolbox for Search-Based Test Generation for Cyber-Physical Systems](https://mlsanity.com/paper/2106.02200/) (2021)
- [Search-based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions](https://mlsanity.com/paper/2207.11016/) (2022)
- [Fast Falsification of Hybrid Systems using Probabilistically Adaptive Input](https://mlsanity.com/paper/1812.04159/) (2018)
- [Wasserstein Generative Adversarial Networks for Online Test Generation for Cyber Physical Systems](https://mlsanity.com/paper/2205.11060/) (2022)
- [Requirement falsification for cyber-physical systems using generative models](https://mlsanity.com/paper/2310.20493/) (2023)
- [MoonLight: A Lightweight Tool for Monitoring Spatio-Temporal Properties](https://mlsanity.com/paper/2104.14333/) (2021)

## Abstract (arXiv)

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 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 textscFlexiFal, 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~citekhandait2024arch.