Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.19397 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914186983899136 |
|---|---|
| author | Zhang, Jiawen Zhang, Zhenwei Zheng, Shun Wen, Xumeng Li, Jia Bian, Jiang |
| author_facet | Zhang, Jiawen Zhang, Zhenwei Zheng, Shun Wen, Xumeng Li, Jia Bian, Jiang |
| contents | Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment surges, a critical blind spot remains: their fragility under adversarial attacks. This lack of scrutiny poses severe risks, particularly as TSFMs enter high-stakes environments vulnerable to manipulation. We present a systematic, diagnostic study arguing that for TSFMs, robustness is not merely a secondary metric but a prerequisite for trustworthy deployment comparable to accuracy. Our evaluation framework, explicitly tailored to the unique constraints of time series, incorporates normalized, sparsity-aware perturbation budgets and unified scale-invariant metrics across white-box and black-box settings. Across six representative TSFMs, we demonstrate that current architectures are alarmingly brittle: even small perturbations can reliably steer forecasts toward specific failure modes, such as trend flips and malicious drifts. We uncover TSFM-specific vulnerability patterns, including horizon-proximal brittleness, increased susceptibility with longer context windows, and weak cross-model transfer that points to model-specific failure modes rather than generic distortions. Finally, we show that simple adversarial fine-tuning offers a cost-effective path to substantial robustness gains, even with out-of-domain data. This work bridges the gap between TSFM capabilities and safety constraints, offering essential guidance for hardening the next generation of forecasting systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19397 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains Zhang, Jiawen Zhang, Zhenwei Zheng, Shun Wen, Xumeng Li, Jia Bian, Jiang Machine Learning Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment surges, a critical blind spot remains: their fragility under adversarial attacks. This lack of scrutiny poses severe risks, particularly as TSFMs enter high-stakes environments vulnerable to manipulation. We present a systematic, diagnostic study arguing that for TSFMs, robustness is not merely a secondary metric but a prerequisite for trustworthy deployment comparable to accuracy. Our evaluation framework, explicitly tailored to the unique constraints of time series, incorporates normalized, sparsity-aware perturbation budgets and unified scale-invariant metrics across white-box and black-box settings. Across six representative TSFMs, we demonstrate that current architectures are alarmingly brittle: even small perturbations can reliably steer forecasts toward specific failure modes, such as trend flips and malicious drifts. We uncover TSFM-specific vulnerability patterns, including horizon-proximal brittleness, increased susceptibility with longer context windows, and weak cross-model transfer that points to model-specific failure modes rather than generic distortions. Finally, we show that simple adversarial fine-tuning offers a cost-effective path to substantial robustness gains, even with out-of-domain data. This work bridges the gap between TSFM capabilities and safety constraints, offering essential guidance for hardening the next generation of forecasting systems. |
| title | Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.19397 |