English

Formally Explaining Neural Networks within Reactive Systems

Artificial Intelligence 2023-10-06 v3 Machine Learning Logic in Computer Science

Abstract

Deep neural networks (DNNs) are increasingly being used as controllers in reactive systems. However, DNNs are highly opaque, which renders it difficult to explain and justify their actions. To mitigate this issue, there has been a surge of interest in explainable AI (XAI) techniques, capable of pinpointing the input features that caused the DNN to act as it did. Existing XAI techniques typically face two limitations: (i) they are heuristic, and do not provide formal guarantees that the explanations are correct; and (ii) they often apply to ``one-shot'' systems, where the DNN is invoked independently of past invocations, as opposed to reactive systems. Here, we begin bridging this gap, and propose a formal DNN-verification-based XAI technique for reasoning about multi-step, reactive systems. We suggest methods for efficiently calculating succinct explanations, by exploiting the system's transition constraints in order to curtail the search space explored by the underlying verifier. We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art. We also demonstrate that our methods produce formal explanations that are more reliable than competing, non-verification-based XAI techniques.

Keywords

Cite

@article{arxiv.2308.00143,
  title  = {Formally Explaining Neural Networks within Reactive Systems},
  author = {Shahaf Bassan and Guy Amir and Davide Corsi and Idan Refaeli and Guy Katz},
  journal= {arXiv preprint arXiv:2308.00143},
  year   = {2023}
}

Comments

To appear in Proc. 23rd Int. Conf. on Formal Methods in Computer-Aided Design (FMCAD)

R2 v1 2026-06-28T11:44:57.896Z