AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ji, Xiayan, Xue, Anton, Wong, Eric, Sokolsky, Oleg, Lee, Insup
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916463494823936
author Ji, Xiayan
Xue, Anton
Wong, Eric
Sokolsky, Oleg
Lee, Insup
author_facet Ji, Xiayan
Xue, Anton
Wong, Eric
Sokolsky, Oleg
Lee, Insup
contents Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing methods and recent advances in generative models to introduce counterfactual explanations for anomaly detection. Given an input, we generate its counterfactual as a diffusion-based repair that shows what a non-anomalous version should have looked like. A key advantage of this approach is that it enables a domain-independent formal specification of explainability desiderata, offering a unified framework for generating and evaluating explanations. We demonstrate the effectiveness of our anomaly explainability framework, AR-Pro, on vision (MVTec, VisA) and time-series (SWaT, WADI, HAI) anomaly datasets. The code used for the experiments is accessible at: https://github.com/xjiae/arpro.
format Preprint
id arxiv_https___arxiv_org_abs_2410_24178
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
Ji, Xiayan
Xue, Anton
Wong, Eric
Sokolsky, Oleg
Lee, Insup
Machine Learning
Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing methods and recent advances in generative models to introduce counterfactual explanations for anomaly detection. Given an input, we generate its counterfactual as a diffusion-based repair that shows what a non-anomalous version should have looked like. A key advantage of this approach is that it enables a domain-independent formal specification of explainability desiderata, offering a unified framework for generating and evaluating explanations. We demonstrate the effectiveness of our anomaly explainability framework, AR-Pro, on vision (MVTec, VisA) and time-series (SWaT, WADI, HAI) anomaly datasets. The code used for the experiments is accessible at: https://github.com/xjiae/arpro.
title AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
topic Machine Learning
url https://arxiv.org/abs/2410.24178