# Compositional Falsification of Cyber-Physical Systems with Machine Learning Components

arXiv: https://arxiv.org/abs/1703.00978 · HTML: https://mlsanity.com/paper/1703.00978/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 30 of 32)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Verification of Image-based Neural Network Controllers Using Generative Models](https://mlsanity.com/paper/2105.07091/) (2021)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles](https://mlsanity.com/paper/2103.07403/) (2021)
- [Benchmarking Safety Monitors for Image Classifiers with Machine Learning](https://mlsanity.com/paper/2110.01232/) (2021)
- [Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review](https://mlsanity.com/paper/2110.08664/) (2021)
- [Testing Rare Downstream Safety Violations via Upstream Adaptive Sampling of Perception Error Models](https://mlsanity.com/paper/2209.09674/) (2022)
- [Part-X: A Family of Stochastic Algorithms for Search-Based Test Generation with Probabilistic Guarantees](https://mlsanity.com/paper/2110.10729/) (2021)
- [Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence](https://mlsanity.com/paper/2506.23908/) (2025)
- [Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning](https://mlsanity.com/paper/2104.10219/) (2021)
- [Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic](https://mlsanity.com/paper/2206.14372/) (2022)
- [Risk-Driven Design of Perception Systems](https://mlsanity.com/paper/2205.10677/) (2022)
- [A Comprehensive Safety Metric to Evaluate Perception in Autonomous Systems](https://mlsanity.com/paper/2512.14367/) (2025)
- [Local Repair of Neural Networks Using Optimization](https://mlsanity.com/paper/2109.14041/) (2021)
- [A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems](https://mlsanity.com/paper/2303.05394/) (2023)
- [Safety Monitoring of Machine Learning Perception Functions: a Survey](https://mlsanity.com/paper/2412.06869/) (2024)
- [Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios](https://mlsanity.com/paper/2504.13478/) (2025)
- [ScenicProver: A Framework for Compositional Probabilistic Verification of Learning-Enabled Systems](https://mlsanity.com/paper/2511.02164/) (2025)
- [STEAM & MoSAFE: SOTIF Error-and-Failure Model & Analysis for AI-Enabled Driving Automation](https://mlsanity.com/paper/2312.09559/) (2023)
- [Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems](https://mlsanity.com/paper/2406.17066/) (2024)
- [Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2603.12183/) (2026)
- [Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics](https://mlsanity.com/paper/2608.06481/) (2026)
- [Adversarial Robustness Verification and Attack Synthesis in Stochastic Systems](https://mlsanity.com/paper/2110.02125/) (2021)
- [Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulations](https://mlsanity.com/paper/2301.01594/) (2023)
- [Worrisome Properties of Neural Network Controllers and Their Symbolic Representations](https://mlsanity.com/paper/2307.15456/) (2023)
- [Evolution of Natural Language Processing Technology: Not Just Language Processing Towards General Purpose AI](https://mlsanity.com/paper/2310.06228/) (2023)
- [Towards provable probabilistic safety for scalable embodied AI systems](https://mlsanity.com/paper/2506.05171/) (2025)
- [Synchronous Signal Temporal Logic for Decidable Verification of Cyber-Physical Systems](https://mlsanity.com/paper/2603.25531/) (2026)
- [Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation](https://mlsanity.com/paper/2609.27296/) (2026)

## Abstract (arXiv)

Cyber-physical systems (CPS), such as automotive systems, are starting to include sophisticated machine learning (ML) components. Their correctness, therefore, depends on properties of the inner ML modules. While learning algorithms aim to generalize from examples, they are only as good as the examples provided, and recent efforts have shown that they can produce inconsistent output under small adversarial perturbations. This raises the question: can the output from learning components can lead to a failure of the entire CPS? In this work, we address this question by formulating it as a problem of falsifying signal temporal logic (STL) specifications for CPS with ML components. We propose a compositional falsification framework where a temporal logic falsifier and a machine learning analyzer cooperate with the aim of finding falsifying executions of the considered model. The efficacy of the proposed technique is shown on an automatic emergency braking system model with a perception component based on deep neural networks.