VeriX: Towards Verified Explainability of Deep Neural Networks

“VeriX: Towards Verified Explainability of Deep Neural Networks” by Min Wu, Haoze Wu, and Clark Barrett. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), (A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, eds.), 2023, pp. 22247-22268.

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.

BibTeX entry:

@inproceedings{WWB23,
   author = {Min Wu and Haoze Wu and Clark Barrett},
   editor = {A. Oh and T. Neumann and A. Globerson and K. Saenko and M.
	Hardt and S. Levine},
   title = {VeriX: Towards Verified Explainability of Deep Neural Networks},
   booktitle = {Advances in Neural Information Processing Systems 36
	(NeurIPS 2023)},
   volume = {36},
   pages = {22247--22268},
   publisher = {Curran Associates, Inc.},
   year = {2023},
   url =
	{https://proceedings.neurips.cc/paper_files/paper/2023/file/46907c2ff9fafd618095161d76461842-Paper-Conference.pdf}
}

(This webpage was created with bibtex2web.)