paper-with-me

홈 › Papers

Adversarial Robustness of Deep State Space Models for Forecasting

2026-04-03 · Sribalaji C. Anand, George J. Pappas arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.03427

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Robust Probabilistic Time Series Forecasting

2022-02-24 · Taeho Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang

Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties. Deep forecasting models, however, could be prone to input perturbations, and th…

Decision MakingProbabilistic Time Series ForecastingTime SeriesTime Series Analysis+1

Quantifying Robustness: A Benchmarking Framework for Deep Learning Forecasting in Cyber-Physical Systems

2025-04-04 · Alexander Windmann, Henrik Steude, Daniel Boschmann, Oliver Niggemann

Cyber-Physical Systems (CPS) in domains such as manufacturing and energy distribution generate complex time series data crucial for Prognostics and Health Management (PHM). While Deep Learning (DL) methods have demonstra…

BenchmarkingModel SelectionState Space Models

Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models

2022-10-05 · Fan Liu, Hao liu, Wenzhao Jiang

Machine learning based traffic forecasting models leverage sophisticated spatiotemporal auto-correlations to provide accurate predictions of city-wide traffic states. However, existing methods assume a reliable and unbia…

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting

2022-08-05 · Juyong Jiang, Binqing Wu, Ling Chen, Kai Zhang 외

Traffic forecasting is an essential problem in urban planning and computing. The complex dynamic spatial-temporal dependencies among traffic objects (e.g., sensors and road segments) have been calling for highly flexible…

Time SeriesTime Series Analysis

Targeted Adversarial Attacks on Wind Power Forecasts

2023-03-29 · René Heinrich, Christoph Scholz, Stephan Vogt, Malte Lehna

In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine …

Adversarial Robustness