AI RESEARCH
Adversarial Robustness of Deep State Space Models for Forecasting
arXiv CS.LG
•
ArXi:2604.03427v1 Announce Type: new State-space model (SSM) for time-series forecasting have nstrated strong empirical performance on benchmark datasets, yet their robustness under adversarial perturbations is poorly understood. We address this gap through a control-theoretic lens, focusing on the recently proposed Spacetime SSM forecaster. We first establish that the decoder-only Spacetime architecture can represent the optimal Kalman predictor when the underlying data-generating process is autoregressive - a property no other SSM possesses.