Time-Series Anomaly Detection

Ask about this topic

Overview

Time-series anomaly detection seeks unusual points, intervals, or changes in relationships among signals, often when labeled failures are scarce and early warnings matter. Common approaches forecast or reconstruct normal behavior and flag large residuals; others use density models, learned representations, graphs, causal structure, or ensembles to capture dependencies and changing operating regimes. Research spans univariate and multivariate benchmarks as well as industrial, medical, network, and edge-device settings, with growing attention to localization, explanations, and compute limits. A central tension is that results depend heavily on evaluation metrics, thresholds, windowing, and anomaly types, while strong benchmark scores may not carry over to distribution shifts or real-time deployment.

Latest papers

CardsList

208 papers35 papers in the last four weeks, up 169% on the four weeks before. 0.2% of all new papers.

  1. BoundAD: Boundary-Aware Negative Generation for Time Series Anomaly Detection

    Mar 18, 2026Xiancheng Wang, Lin Wang, Zhibo Zhang +2Time-Series Anomaly DetectionUnsupervised Anomaly Detection

    School of Ocean Engineering, Harbin Institute of Technology, West Wenhua Road, Weihai, 264209, Shandong, China. · Technical Center, Bogie Development Department, CRRC Qingdao Sifang Locomotive and Rolling Stock Co., Ltd., Jinhong East Road, Qingdao, 266111, Shandong, China.

  2. When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry

    Mar 17, 2026Michael Bidollahkhani, Freja Nordsiek, Julian M. KunkelFault DetectionPredictive Maintenance

    Gesellschaft für wissenschaftliche Datenverarbeitung mbH Göttingen (GWDG) Georg-August-Universität Göttingen Göttingen, Germany

  3. Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

    Mar 13, 2026Kadir-Kaan Özer, René Ebeling, Markus EnzweilerLLM-Based Time Series Anomaly DetectionTime-Series Anomaly Detection

    Mercedes-Benz AG, Germany · Institute for Intelligent Systems, Esslingen University of Applied Sciences, Germany

  4. On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines

    Mar 13, 2026Francesco Maione, Paolo Lino, Giuseppe Giannino +1Fault DetectionTime-Series Anomaly Detection

  5. Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows

    Mar 12, 2026David Baumgartner, Eliezer de Souza da Silva, Iñigo UrteagaNormalizing FlowsLatent Dynamics Modeling

    Department of Computer Science, Norwegian University of Science and Technology, Norway · BCAM — Basque Center for Applied Mathematics, Spain · Department of Informatics Engineering, University of Coimbra, Portugal +2

  6. CINDI: Conditional Imputation and Noisy Data Integrity with Flows in Power Grid Data

    Mar 12, 2026David Baumgartner, Helge Langseth, Heri RamampiaroTime Series ImputationTime-Series Anomaly Detection

    Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway

  7. ECoLAD: Selecting Anomaly Detectors for Automotive Deployment via Compute-Reduction Evaluation

    Mar 11, 2026Kadir-Kaan Özer, René Ebeling, Markus EnzweilerEfficient Neural Network InferenceAutomated Evaluation

    Mercedes-Benz AG, Germany. · Esslingen University of Applied Sciences, Germany.

  8. Detecting Abnormal User Feedback Patterns through Temporal Sentiment Aggregation

    Mar 11, 2026Yalun Qi, Sichen Zhao, Zhiming Xue +2Anomaly DetectionTime-Series Anomaly Detection

    Khoury College of Computer Science Northeastern University Boston United States · College of Engineering Northeastern University Boston United States · College of Professional Studies Northeastern University Boston United States

  9. 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

  10. Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection

    Mar 10, 2026David Baumgartner, Helge Langseth, Kenth Engø-Monsen +1Time-Series Anomaly DetectionNormalizing Flows

    Department of Computer Science, Norwegian University of Science and Technology.

  11. 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

  12. DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection

    Mar 6, 2026Yuewei Li, Dalin Zhang, Huan Li +3Time-Series Anomaly DetectionAnomaly Detection

    Hangzhou Dianzi University, Hangzhou, China · Zhejiang University, Hangzhou, China

  13. Unsupervised Anomaly Detection in Wearable Foot Sensor Data: A Baseline Feasibility Study Towards Diabetic Foot Ulcer Prevention

    Feb 27, 2026Md Tanvir Hasan TurjaUnsupervised Anomaly DetectionWearable Health Monitoring

    Department of Computer Science, Middlesex University London, London, UK

  14. Selective Denoising Diffusion Model for Time Series Anomaly Detection

    Feb 27, 2026Kohei Obata, Zheng Chen, Yasuko Matsubara +2LLM-Based Time Series Anomaly DetectionTime-Series Anomaly Detection

    SANKEN, The University of Osaka, Osaka, Japan · Great Bay University, Dongguan, China

  15. RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms

    Feb 25, 2026Mohamed Abdelmaksoud, Sheng Ding, Andrey Morozov +1Time-Series Anomaly Detection

    BIFOLD & TU Berlin Berlin, Germany · University of Stuttgart Stuttgart, Germany

  16. CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detection

    Feb 24, 2026Zhongpeng Qi, Jun Zhang, Wei Li +1Time-Series Anomaly DetectionGraph Contrastive Learning

    Dalian Maritime University, Dalian, China · Harbin Engineering University, Harbin, China

  17. TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection

    Feb 22, 2026Hui He, Hezhe Qiao, Yutong Chen +2Time-Series Anomaly DetectionUnsupervised Anomaly Detection

    School of Computing and Information Systems, Singapore Management University, Singapore · Chongqing Institute of Green and Intelligent Technology, University of Chinese Academy of Sciences, Chongqing, China · State Information Center, Beijing, China

  18. Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles

    Feb 19, 2026Hyeongwon Kang, Jinwoo Park, Seunghun Han +1Early Warning DetectionTime-Series Anomaly Detection

    Department of Industrial & Management Engineering, Korea University, 126-16 Anam-dong 5-ga, Seongbuk-gu, Seoul, Republic of Korea · Department of Industrial Engineering, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul, Republic of Korea · LG CNS, 71, Magokjungang 8-ro, Gangseo-gu, Seoul, Republic of Korea

  19. VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

    Feb 18, 2026Yingyuan Yang, Tian Lan, Yifei Gao +6Time-Series Anomaly DetectionZero-Shot Anomaly Detection

    Department of Industrial Engineering, Tsinghua University, Beijing, China · Lab, Huawei Technologies Ltd, Beijing, China · Datadog AI Research.

  20. Benchmarking IoT Time-Series AD with Event-Level Augmentations

    Feb 17, 2026Dmitry Zhevnenko, Ilya Makarov, Aleksandr Kovalenko +6Time-Series Anomaly DetectionAnomaly Detection

    AXXX, Moscow, Russia · Research Center of the Artificial Intelligence Institute, Innopolis University, Innopolis, Russia · Trusted AI Center, RAS, Moscow, Russia +1

  21. LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection

    Feb 9, 2026Dezheng Wang, Tong Chen, Guansong Pang +3Multi-View LearningUnsupervised Anomaly Detection

    School of Automation, Southeast University Nanjing, China · School of Electrical Engineering and Computer Science, The University of Queensland Brisbane, Australia · School of Computing and Information Systems, Singapore Management University Singapore

  22. PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection

    Feb 1, 2026Jinju Park, Seokho KangSelf-Supervised Time Series Representation LearningTime Series Representation Learning

    Department of Industrial Engineering, Sungkyunkwan University

  23. Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failures

    Jan 30, 2026Saeid Jamshidi, Foutse Khomh, Carol Fung +2Time-Series Anomaly DetectionSpatiotemporal GNNs

    SWAT Laboratory, Polytechnique Montréal, Québec, Canada · CIISE, Concordia University, Montréal, QC, Canada · Department of Computer Engineering and Software Engineering, Polytechnique Montréal, Québec, Canada +1

  24. COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing

    Nov 10, 2025Wenlong Shang, Shihao Tian, Xutong Wan +1Reconstruction-Based Anomaly DetectionTime-Series Anomaly Detection

    School of Information Science and Technology, Beijing University of Technology, China · Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, China

  25. 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

  26. SPADE: A Large Language Model Framework for Soil Moisture Pattern Recognition and Anomaly Detection in Precision Agriculture

    Sep 10, 2025Yeonju Lee, Rui Qi Chen, Joseph Oboamah +7Zero-Shot Anomaly DetectionTime-Series Anomaly Detection

    H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA · Panhandle Research and Extension Center, University of Nebraska-Lincoln, Scottsbluff, NE, USA · Department of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA +3

  27. Signature-Kernel One-Class Learning with Manifold Regularisation for Multivariate Time Series Anomaly Detection

    Jul 31, 2025Shervin Rahimzadeh ArashlooTime-Series Anomaly DetectionOne-Class Classification

    Department of Computer Engineering, Faculty of Engineering, Bilkent University, Ankara, Turkey.

  28. FANTF: Fuzzy attention network based transformers for time series analysis

    Mar 31, 2025Sanjay Chakraborty, Fredrik HeintzTime Series TransformersTime Series Forecasting

    Department of Computer and Information Science (IDA), REAL, AIICS, Linköping University, Linköping, Sweden