Exploring Zero-Shot Foundation Models for Multivariate Time Series Anomaly Detection

2026-07-14 · Martin Uray, Saverio Messineo, Roland Kwitt, Stefan Huber arxiv

Multivariate Time Series Anomaly Detection (MTSAD) is essential for reliability and safety in domains such as industrial process monitoring and financial risk management, yet conventional approaches rely on application-specific models that are costly to train and hard to scale. Foundation Models (FMs), pre-trained on broad data with strong zero-shot generalization, have recently become available for univariate time series forecasting, raising the question of whether they can address MTSAD without task-specific training. We investigate the zero-shot application of a univariate forecasting FM, TimesFM, to industrial MTSAD on the Secure Water Treatment (SWaT) benchmark, evaluating two strategies: treating the FM as a per-feature forecaster with thresholded prediction errors, and as an embedder whose intermediate representations feed standard outlier detectors. Neither of our proposed setups is competitive with established baselines; embeddings reveal only partial separation between normal and anomalous segments, insufficient for reliable detection. The cause is that the FM is too effective at capturing temporal dynamics, yielding low error even within fully anomalous windows, so persistent anomalies become indistinguishable from normal behavior. However, these observations yield valuable insights: the error peaks at anomaly boundaries, indicating FMs reliably detect distribution changes. We conclude that the proposed naive zero-shot FMs are unsuitable for MTSAD but promising for change-point detection.

📄 PDF Abstract BibTeX arXiv:2607.12454

Code (0)

등록된 구현이 없습니다.

Tasks

Univariate Time Series Forecasting Time Series Anomaly Detection Zero-shot Generalization

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

2024-02-12 · Cheng Feng, Long Huang, Denis Krompass

We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning…

Multivariate Time Series Forecasting Time Series Time Series Forecasting

Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks

2026-04-09 · Mayuka Jayawardhana, Nihal Sharma, Kazem Meidani, Bayan Bruss 외 arxiv

Tabular foundation models, particularly Prior-data Fitted Networks like TabPFN have emerged as the leading contender in a myriad of tasks ranging from data imputation to label prediction on the tabular data format surpas…

Multivariate Time Series Forecasting Univariate Time Series Forecasting

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

2026-07-07 · Qian Sun, Yong-Ming Tian, Jia-Wei Huang, Cheng Feng 외 arxiv

Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on m…

Zero-shot Generalization

Forecast2Anomaly (F2A): Adapting Multivariate Time Series Foundation Models for Anomaly Prediction

2025-11-05 · Atif Hassan, Tarun Kumar, Ashish Mishra, Sergey Serebryakov 외 arxiv

Forecasting anomalies (anomaly prediction) in multivariate time series from different real-world, dynamic, and complex systems is vital for preempting critical failures, leading to a substantial minimization in operation…

Performance of Zero-Shot Time Series Foundation Models on Cloud Data

2025-02-18 · William Toner, Thomas L. Lee, Artjom Joosen, Rajkarn Singh 외

Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. FMs are trained on numerous diverse datasets and claim to be effective forecasters across multiple different …

Time Series