Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
This work addresses a critical safety gap for users of TSFMs in deployment scenarios, highlighting vulnerabilities that could be exploited in attacks, though it is incremental in focusing on robustness rather than core forecasting performance.
The study investigated the adversarial robustness of Time Series Foundation Models (TSFMs) and found that minimal input perturbations can cause significant and controllable forecast errors like trend reversal and amplitude shift, posing serious risks to real-world applications.
Time Series Foundation Models (TSFMs), which are pretrained on large-scale, cross-domain data and capable of zero-shot forecasting in new scenarios without further training, are increasingly adopted in real-world applications. However, as the zero-shot forecasting paradigm gets popular, a critical yet overlooked question emerges: Are TSFMs robust to adversarial input perturbations? Such perturbations could be exploited in man-in-the-middle attacks or data poisoning. To address this gap, we conduct a systematic investigation into the adversarial robustness of TSFMs. Our results show that even minimal perturbations can induce significant and controllable changes in forecast behaviors, including trend reversal, temporal drift, and amplitude shift, posing serious risks to TSFM-based services. Through experiments on representative TSFMs and multiple datasets, we reveal their consistent vulnerabilities and identify potential architectural designs, such as structural sparsity and multi-task pretraining, that may improve robustness. Our findings offer actionable guidance for designing more resilient forecasting systems and provide a critical assessment of the adversarial robustness of TSFMs.