Time-Series Anomaly Detection

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

228 papers27 papers in the last four weeks, down 16% on the four weeks before. 0.2% of all new papers.

  1. 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

  2. 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

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

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

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

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

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

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

  6. AnomaMind: Coarse-to-Fine Agentic Diagnosis via Hybrid Inference for Time Series Anomaly Detection

    Feb 14, 2026Xiaoyu Tao, Yuchong Wu, Mingyue Cheng +2Time-Series Anomaly DetectionLLM-Based Time Series Anomaly Detection

  7. 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

  8. COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection

    Feb 2, 2026Jinwoo Park, Hyeongwon Kang, Seung Hun Han +1Unsupervised Anomaly DetectionTime-Series Anomaly Detection

  9. 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

  10. Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection: An Empirical Study and Minimalist Baseline

    Nov 20, 2025Zhijie Zhong, Zhiwen Yu, Kaixiang Yang +3Time-Series Anomaly Detection

  11. 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

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

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

  13. Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

    Sep 25, 2025Tian Lan, Hao Duong Le, Jinbo Li +4Time-Series Anomaly DetectionTime-Series Foundation Models

  14. 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

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

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

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

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

  17. Deep learning for structural health monitoring: An application to heritage structures

    Nov 4, 2022Fabio Carrara, Fabrizio Falchi, Maria Girardi +3Structural Health MonitoringAnomaly Detection