Interpretable Anomaly Detection

Overview

Interpretable anomaly detection studies how to identify unusual observations or events while making clear why they were flagged. Approaches include intrinsically readable rules, prototypes and symbolic models, as well as feature attribution, counterfactuals, and language-based explanations layered onto deep detectors. These methods are used with images, time series, graphs, and tabular data in settings such as industrial monitoring, cybersecurity, healthcare, and scientific discovery, where explanations can guide investigation and response. A central challenge is ensuring that explanations are faithful and useful without reducing detection accuracy, especially as data and operating conditions shift.

Latest papers

CardsList

84 papers15 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

  1. How to Explain your Unexplainable Video Anomaly Detector

    Nov 16, 2026Giacomom D'Amicantonio, Egor BondarevInterpretable Anomaly DetectionCounterfactual Explanations

  2. Flow-CAD: Flow Matching for Contextual Anomaly Detection and Explanation in Tabular Data

    Nov 12, 2026Zhong Li, Qi Huang, Yuhang Wang +5Contextual Anomaly DetectionTabular Anomaly Detection

  3. PIA: Agentic Physics-Informed Runtime Anomaly Detection

    Nov 7, 2026Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis KarimipourAnomaly DetectionCPS Security

  4. AnomSep: Bridging Optimization-Based Separation and Deep Neural Refinement for Anomaly Detection with Listenable Explanations

    Nov 6, 2026Koki Shoda, Jun Younes Louhi Kasahara, Qi An +1Anomaly DetectionInterpretable Anomaly Detection

  5. Spatiotemporal Dynamics-Aware Industrial Anomaly Detection and Reasoning

    Nov 5, 2026S-Wei Chen, Siangyu Yang, Yi-Chen Jan +2Industrial Anomaly DetectionAnomaly Detection

  6. INSIGHT-HPC: An Interpretable System Intelligence for Global HPC Telemetry

    Nov 2, 2026Rupak Kadel, Jie Li, Yong ChenAnomaly DetectionInterpretable Anomaly Detection

  7. A Unified XAI-NSAI Analytical Framework for Trustworthy IoT Anomaly Detection

    Oct 30, 2026Hugues Leger, Giovani R. AbuaitahInterpretable Anomaly DetectionAnomaly Detection

  8. TGTV: An Interpretable Framework for UAV Fault Detection and Traceability via Spatiotemporal Graph Learning and Large Language Models

    Oct 28, 2026Zixuan Wang, Changbo Shi, Ji LiuFault DetectionFault Diagnosis

  9. ReForest: Interpretability Meets Reasoning in Isolation Forest

    Oct 27, 2026Juyoung Seo, Geonwoo Bang, Dongho Kim +1Contextual Anomaly DetectionAnomaly Detection

  10. AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection

    Oct 26, 2026Van Kwan Zhi Koh, Songnan Lin, Rongmo Luo +2Time-Series Anomaly DetectionInterpretable Anomaly Detection

  11. SGDB: Semantic-Geometric Decoupling and Evidence Binding for Logical Anomaly Detection

    Oct 26, 2026Chenrui Ji, Jiafan Lu, Zilu Luo +3Logical Anomaly DetectionAnomaly Detection

  12. AnomalyJev: Towards Evaluating Image Anomaly Explanations via Claim-Level Verification

    Oct 20, 2026Qizhou Wang, Jiawen Zhu, Guansong Pang +1Explainability EvaluationInterpretable Anomaly Detection

  13. BEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly Detection

    Oct 20, 2026Zhe Li, Tengxue Zhang, Yang Shu +4Anomaly DetectionMultimodal Anomaly Detection

  14. Moment-Based Anomaly Detection in High-Dimensional Mixed Data

    Oct 12, 2026Davide Ferrari, Andrea NicolodiAnomaly DetectionTabular Anomaly Detection

  15. Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC

    Oct 9, 2026Donatella Genovese, Philip Ploner, Simone Scardapane +2Anomaly DetectionInterpretable Anomaly Detection

  16. Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding

    Oct 1, 2026Mohd Ubaid Wani, Sara Atito, Josef Kittler +1CoT ReasoningInterpretable Anomaly Detection

  17. Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability

    Oct 1, 2026Roberto Stanzione, Jules Barbe, Magali Parrino +2Interpretable Anomaly DetectionAnomaly Localization

  18. From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring

    Sep 30, 2026Nicolas Vautier, Paul Caron, Nardi Xhepi +4Interpretable Anomaly DetectionIndustrial Anomaly Detection

  19. Augmenting Visual Anomaly Detection with Automated Interpretability

    Sep 27, 2026Antonio De Santis, Arsenio Leo, Marco Brambillaautomated interpretabilityInterpretable Anomaly Detection

  20. PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning

    Sep 23, 2026Kevin Lee, Alison J. MarchUnsupervised Anomaly DetectionInterpretable Anomaly Detection

  21. Collaborative Streaming Anomaly Detection with Interactive Explanations and Ensemble Consensus

    Sep 20, 2026Diogo Risca, Afonso Lourenço, Ricardo Martins +1Online Anomaly DetectionInterpretable Anomaly Detection

  22. Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection

    Sep 20, 2026Naser Mansour, Sidahmed Benabderrahmane, Ameer RahwanTime-Series Anomaly DetectionInterpretable Anomaly Detection

  23. Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection

    Sep 19, 2026Zhiji Yang, Fangyong Wang, Yue Li +2Semi-Supervised Anomaly DetectionAnomaly Detection

  24. Identifying Security Platform Product Abuse with Machine Learning

    Sep 18, 2026Shaefer Drew, Michael Brautbar, Paul Knight +6Software SecurityAnomaly Detection