Spectral-temporal Decoupled Sparse Attack on Parameter-efficient Time Series Forecasting

Recent advances in time series forecasting (TSF) have embraced architectural minimalism and parameter efficiency, but still achieved competitive accuracy. However, extreme structural sparsity and drastically reduced parameter spaces are vulnerable to adversarial perturbations. In this work, we propose a spectral-temporal decoupled sparse attack on parameter-efficient (PE) TSF models, which simultaneously disrupts localized morphological shapes and dominant periodic trajectories. Extensive experiments show that our method successfully sabotages five state-of-the-art PE TSF models for a small ${\ell }_{\infty }$ perturbation budget $ϵ=0.1$ (SNR$\approx 21.52$dB) without any structural or parameter queries, even under six representative adversarial defense measures. It can be applied to non-query attacks on remote edge-devices, stress testing in critical infrastructure domains, and structural diagnosing on PE edge-device deployment.