VeriX: Towards Verified Explainability of Deep Neural Networks

Min Wu, Haoze Wu, Clark Barrett

Keywords: trustworthy machine learning, deep neural networks, explainability, interpretability, formal methods, automated verification

TL;DR: We present VeriX (Verified Explainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models.

Abstract:

We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models. We build such explanations and counterfactuals iteratively using constraint solving techniques and a heuristic based on feature-level sensitivity ranking. We evaluate our method on image recognition benchmarks and a real-world scenario of autonomous aircraft taxiing.

Submission Number: 9228