AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 40 of its 74 references that are in the map. First posted on arXiv 31 Oct 2024.
Builds on
40 of 74 references.
References · 40
- 2017Attention Is All You Needcited by 59,932
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2022Generative Adversarial Networkscited by 5,603
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2016Wide Residual Networkscited by 3,057
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
- 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
28 more
- 2017Generative Adversarial Networks: An Overviewcited by 588
- 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
- 2023Detecting Language Model Attacks with Perplexitycited by 411
- 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
- 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
- 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
- 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
- 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generationcited by 179
- 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
- 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
- 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
- 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
- 2020Principles and Practice of Explainable Machine Learningcited by 99
- 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Modelscited by 95
- 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
- 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
- 2019Anomaly Detection in Road Traffic Using Visual Surveillance: A Surveycited by 30
- 2021A Survey on Anomaly Detection for Technical Systems using LSTM Networkscited by 27
- 2021DATE: Detecting Anomalies in Text via Self-Supervision of Transformerscited by 25
- 2022Formalising the Robustness of Counterfactual Explanations for Neural Networkscited by 24
- 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
- 2017Anomaly Detection by Robust Statisticscited by 22
- 2023Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstructioncited by 17
- 2022Diverse Counterfactual Explanations for Anomaly Detection in Time Seriescited by 10
- 2020Time Series Data Cleaning: From Anomaly Detection to Anomaly Repairing (Technical Report)cited by 7
- 2023DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Modelscited by 7
- 2022Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoringcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.