Adversarial Robustness of Deep State Space Models for Forecasting

• URL: http://arxiv.org/abs/2604.03427v1
• Date: Fri, 03 Apr 2026 19:53:58 GMT
• Title: Adversarial Robustness of Deep State Space Models for Forecasting
• Abstract summary: State-space model (SSM) for time-series forecasting have demonstrated strong empirical performance on benchmark datasets.<n>We first establish that the decoder-only Spacetime architecture can represent the optimal Kalman predictor when the underlying data-generating process is autoregressive.<n>We derive closed-form bounds on adversarial forecasting error that expose how open-loop instability, closed-loop instability, and decoder state dimension each amplify vulnerability.
• Score: 22.283866173947278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-space model (SSM) for time-series forecasting have demonstrated 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. Building on this, we formulate robust forecaster design as a Stackelberg game against worst-case stealthy adversaries constrained by a detection budget, and solve it via adversarial training. We derive closed-form bounds on adversarial forecasting error that expose how open-loop instability, closed-loop instability, and decoder state dimension each amplify vulnerability - offering actionable principles towards robust forecaster design. Finally, we show that even adversaries with no access to the forecaster can nonetheless construct effective attacks by exploiting the model's locally linear input-output behavior, bypassing gradient computations entirely. Experiments on the Monash benchmark datasets highlight that model-free attacks, without any gradient computation, can cause at least 33% more error than projected gradient descent with a small step size.

Related papers

• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• Foundational World Models Accurately Detect Bimanual Manipulator Failures [21.93685012734004]
  We train a probabilistic, history informed, world model within the compressed latent space of a pretrained vision foundation model.<n>The model outputs uncertainty estimates alongside its predictions that serve as non-conformity scores within a conformal prediction framework.<n>We show that our approach requires approximately one twentieth of the trainable parameters as the next-best learning-based approach.
  arXiv  Detail & Related papers  (2026-03-07T02:11:29Z)
• Dynamic Attention (DynAttn): Interpretable High-Dimensional Spatio-Temporal Forecasting (with Application to Conflict Fatalities) [0.0]
  DynAttn is an interpretable dynamic-attention forecasting framework for high-dimensional count processes.<n>It produces multi-horizon forecasts of expected casualties and exceedance, while retaining transparent diagnostics.<n>Across forecast horizons from one to twelve months, DynAttn consistently achieves substantially higher predictive accuracy.
  arXiv  Detail & Related papers  (2025-12-24T21:47:35Z)
• Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models [60.728124907335]
  This work introduces Weather Adaptive Adversarial Perturbation Optimization (WAAPO), a novel framework for generating targeted adversarial perturbations.<n>WAAPO achieves this by incorporating constraints for channel sparsity, spatial localization, and smoothness, ensuring that perturbations remain physically realistic and imperceptible.<n>Our experiments highlight critical vulnerabilities in AI-driven forecasting models, where small perturbations to initial conditions can result in significant deviations.
  arXiv  Detail & Related papers  (2025-12-09T17:20:56Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction [16.063976106946402]
  We propose Cyc-Attack, a novel method that perturbs the upstream forecasts of DLWF models to generate adversarial trajectories.<n>To overcome these limitations, we propose Cyc-Attack, a novel method that perturbs the upstream forecasts of DLWF models to generate adversarial trajectories.
  arXiv  Detail & Related papers  (2025-10-11T09:42:16Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Trustworthy Pedestrian Trajectory Prediction via Pattern-Aware Interaction Modeling [7.818805084618764]
  InSyn is a novel Transformer-based model that captures diverse interaction patterns.<n>SSOS is a training strategy designed to alleviate the common issue of initial-step divergence in numerical time-series prediction.
  arXiv  Detail & Related papers  (2025-07-16T12:23:04Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM)<n>To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.