# ARTA: Adversarial-Robust Multivariate Time--Series Anomaly Detection via Sparsity-Constrained Perturbations

arXiv: https://arxiv.org/abs/2603.25956 · HTML: https://mlsanity.com/paper/2603.25956/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 11 of 11)

- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [FITS: Modeling Time Series with 10k Parameters](https://mlsanity.com/paper/2307.03756/) (2023)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [COPOD: Copula-Based Outlier Detection](https://mlsanity.com/paper/2009.09463/) (2020)
- [Extended Isolation Forest](https://mlsanity.com/paper/1811.02141/) (2018)
- [Robust PCA for Anomaly Detection in Cyber Networks](https://mlsanity.com/paper/1801.01571/) (2018)
- [Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling](https://mlsanity.com/paper/2311.12550/) (2023)
- [Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels](https://mlsanity.com/paper/2501.11959/) (2025)

## Abstract (arXiv)

Time-series anomaly detection (TSAD) is a critical component in monitoring complex systems, yet modern deep learning-based detectors are often highly sensitive to localized input corruptions and structured noise. We propose ARTA (Adversarially Robust multivariate Time-series Anomaly detection via sparsity-constrained perturbations), a joint training framework that improves detector robustness through a principled min-max optimization objective. ARTA comprises an anomaly detector and a sparsity-constrained mask generator that are trained simultaneously. The generator identifies minimal, task-relevant temporal perturbations that maximally increase the detector's anomaly score, while the detector is optimized to remain stable under these structured perturbations. The resulting masks characterize the detector's sensitivity to adversarial temporal corruptions and can serve as explanatory signals for the detector's decisions. This adversarial training strategy exposes brittle decision pathways and encourages the detector to rely on distributed and stable temporal patterns rather than spurious localized artifacts. We conduct extensive experiments on the TSB-AD benchmark, demonstrating that ARTA consistently improves anomaly detection performance across diverse datasets and exhibits significantly more graceful degradation under increasing noise levels compared to state-of-the-art baselines.