Interpretable Anomaly Detection

Ask about this topic

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

73 papers10 papers in the last four weeks, down 9% on the four weeks before. 0.1% of all new papers.

  1. Unsupervised Symbolic Anomaly Detection

    Mar 18, 2026Md Maruf Hossain, Tim Katzke, Simon Klüttermann +1Unsupervised Anomaly DetectionAnomaly Detection

    TU Dortmund University, Dortmund, Germany · Research Center Trustworthy Data Science and Security, UA Ruhr, Germany

  2. FoMo X: Modular Explainability Signals for Outlier Detection Foundation Models

    Mar 18, 2026Simon Klüttermann, Tim Katzke, Phuong Huong Nguyen +1Interpretable Anomaly DetectionUnsupervised Anomaly Detection

    TU Dortmund University, Dortmund, Germany · Research Center Trustworthy Data Science and Security, University Alliance Ruhr, Dortmund, Germany

  3. Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attention

    Mar 11, 2026Kosti Koistinen, Kirsi Hellsten, Joni Herttuainen +1Industrial Anomaly DetectionIndustrial Control System Security

    Aalto University School of Science Computer Science Department P.O.Box 11000, 00076 AALTO, Finland

  4. GNNs for Time Series Anomaly Detection: An Open-Source Framework and a Critical Evaluation

    Mar 10, 2026Federico Bello, Gonzalo Chiarlone, Marcelo Fiori +2Graph-Based Anomaly DetectionTime-Series Anomaly Detection

    Facultad de Ingeniería, Universidad de la República, Montevideo, Uruguay · Pento, Montevideo, Uruguay · Centro Interdisciplinario en Ciencia de Datos y Aprendizaje Automático (CICADA), Universidad de la República, Uruguay

  5. Explainable Condition Monitoring via Probabilistic Anomaly Detection Applied to Helicopter Transmissions

    Mar 9, 2026Aurelio Raffa Ugolini, Jessica Leoni, Valentina Breschi +4Anomaly DetectionInterpretable Anomaly Detection

    DEIB, Politecnico di Milano Via Giuseppe Ponzio 34, Milano, 20133 (Italy) · Dep. of Electrical Engineering, TU\e Groene Loper 19, Eindhoven, 5600 MB (The Netherlands) · Leonardo Labs, Leonardo S.p.A. Piazza Monte Grappa 4, Roma, 00195 (Italy)

  6. An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series

    Mar 9, 2026Waldyn G MartinezTime-Series Anomaly DetectionInterpretable Anomaly Detection

    Department of Information Systems & Analytics Farmer School of Business Miami University Oxford, OH 45056

  7. Interpretable Maximum Margin Deep Anomaly Detection

    Mar 7, 2026Zhiji Yang, Mei Huang, Xinyu Li +3Semi-Supervised Anomaly DetectionAnomaly Detection

    the School of Statistics and Mathematics, Yunnan University of Finance and Economics, Kunming 650221, China · the Academy for Multidisciplinary Studies, Capital Normal University, Beijing 100048, China

  8. Trivial Graph Features and Classical Learning are Enough to Detect Random Anomalies

    Mar 2, 2026Matthieu Latapy, Stephany RajehAnomaly DetectionGraph-Based Anomaly Detection

    CNRS, LIP6 Sorbonne Universit´e Paris, France · Efrei Research Lab Efrei Paris Panth´eon-Assas Universit´e Villejuif, France

  9. Multi-Axis Trust Modeling for Interpretable Account Hijacking Detection

    Feb 20, 2026Mohammad AL-SmadiAnomaly DetectionInterpretable Anomaly Detection

    Qatar University, Doha, Qatar

  10. Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance

    Feb 17, 2026Rebin Saleh, Khanh Pham Dinh, Balázs Villányi +1Predictive MaintenanceIndustrial Anomaly Detection

    Department of Electronics Technology, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3, H-1111 Budapest, Hungary · DataScienceWorld.Kan, Hanoi, Vietnam · Department of Computer Science, The University of Alabama at Birmingham, 1720 University Blvd, Birmingham, AL 35294 USA

  11. Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning

    Feb 10, 2026Peng Chen, Wenqiang Wang, Yunkang Cao +7Industrial Anomaly DetectionMultimodal Anomaly Detection

    School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China · Department of Computer and Information Science, University of Macau, Macau, China

  12. Explainable Visual Anomaly Detection via Concept Bottleneck Models

    Nov 25, 2025Arianna Stropeni, Valentina Zaccaria, Francesco Borsatti +3Interpretable Anomaly DetectionAnomaly Localization

    University of Padova, Italy

  13. Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection

    Oct 18, 2025Dongchan Cho, Jiho Han, Keumyeong Kang +3Time-Series Anomaly DetectionUnsupervised Anomaly Detection

    Industrial AI Lab, SimPlatform Co. Ltd. Affiliate Research Institute