paper-with-me

홈 › Papers

VeriX: Towards Verified Explainability of Deep Neural Networks

2022-12-02 · NeurIPS 2023 11

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.

📄 PDF Abstract BibTeX arXiv:2212.01051

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

Better Verified Explanations with Applications to Incorrectness and Out-of-Distribution Detection

2024-09-04 · Min Wu, Xiaofu Li, Haoze Wu, Clark Barrett

Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning model outputs, we present VeriX+, which significantly improves both the size and th…

Out-of-Distribution Detection

MAVERIX: Multimodal Audio-Visual Evaluation Reasoning IndeX

2025-03-27 · Liuyue Xie, George Z. Wei, Avik Kuthiala, Ce Zheng 외

Frontier models have either been language-only or have primarily focused on vision and language modalities. Although recent advancements in models with vision and audio understanding capabilities have shown substantial p…

Decision Making

FAME: Formal Abstract Minimal Explanation for Neural Networks

2026-03-11 · Ryma Boumazouza, Raya Elsaleh, Melanie Ducoffe, Shahaf Bassan 외 arxiv

We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural networks while reducing explanation siz…

VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymization

2026-04-14 · Miit Daga, Swarna Priya Ramu arxiv

Organisations increasingly outsource privacy-sensitive data transformations to cloud providers, yet no practical mechanism lets the data owner verify that the contracted algorithm was faithfully executed. VeriX-Anon is a…

Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis

2022-02-15 · CVPR 2023 1 · Thomas Fel, Melanie Ducoffe, David Vigouroux, Remi Cadene 외

A variety of methods have been proposed to try to explain how deep neural networks make their decisions. Key to those approaches is the need to sample the pixel space efficiently in order to derive importance maps. Howev…