A New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems

Abstract

Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This dominance stems from the limited scalability of existing backward reachability methods. In this work, we introduce new algorithms that compute both over- and under-approximations of backward reachable sets for such systems. We further integrate these backward algorithms with established forward analysis techniques to yield a unified verification framework for neural feedback systems.

Accepted to AAAI-2026 Bridge Program B10: Making Embodied AI Reliable with Testing and Formal Verification