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

arXiv: https://arxiv.org/abs/2607.12454 · HTML: https://mlsanity.com/paper/2607.12454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series](https://mlsanity.com/paper/2109.11428/) (2021)
- [Foundation Models for Time Series: A Survey](https://mlsanity.com/paper/2504.04011/) (2025)
- [Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?](https://mlsanity.com/paper/2405.02678/) (2024)
- [Open Challenges in Time Series Anomaly Detection: An Industry Perspective](https://mlsanity.com/paper/2502.05392/) (2025)
- [Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate](https://mlsanity.com/paper/2606.02670/) (2026)
- [Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation](https://mlsanity.com/paper/2605.27486/) (2026)
- [ChronosAD: Leveraging Time Series Foundation Models for Accurate Anomaly Detection](https://mlsanity.com/paper/2606.01300/) (2026)
- [Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs](https://mlsanity.com/paper/2606.18898/) (2026)

## Abstract (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.