VeriX: Towards Verified Explainability of Deep Neural Networks
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.
Cite
Text
Wu et al. "VeriX: Towards Verified Explainability of Deep Neural Networks." Neural Information Processing Systems, 2023.Markdown
[Wu et al. "VeriX: Towards Verified Explainability of Deep Neural Networks." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/wu2023neurips-verix/)BibTeX
@inproceedings{wu2023neurips-verix,
title = {{VeriX: Towards Verified Explainability of Deep Neural Networks}},
author = {Wu, Min and Wu, Haoze and Barrett, Clark},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/wu2023neurips-verix/}
}