Temporally Unified Adversarial Perturbations for Time Series Forecasting

TL;DR

This paper introduces TUAPs, a method for generating temporally consistent adversarial perturbations in time series forecasting, improving attack effectiveness while maintaining temporal coherence across overlapping samples.

Contribution

We propose TUAPs with a novel temporal unification constraint and a gradient accumulation method, enhancing adversarial attack consistency and efficiency in time series models.

Findings

Outperforms baseline attacks in white-box scenarios

Effective in black-box transfer attacks

Maintains temporal consistency across samples

Abstract

While deep learning models have achieved remarkable success in time series forecasting, their vulnerability to adversarial examples remains a critical security concern. However, existing attack methods in the forecasting field typically ignore the temporal consistency inherent in time series data, leading to divergent and contradictory perturbation values for the same timestamp across overlapping samples. This temporally inconsistent perturbations problem renders adversarial attacks impractical for real-world data manipulation. To address this, we introduce Temporally Unified Adversarial Perturbations (TUAPs), which enforce a temporal unification constraint to ensure identical perturbations for each timestamp across all overlapping samples. Moreover, we propose a novel Timestamp-wise Gradient Accumulation Method (TGAM) that provides a modular and efficient approach to effectively generate TUAPs by aggregating local gradient information from overlapping samples. By integrating TGAM with momentum-based attack algorithms, we ensure strict temporal consistency while fully utilizing series-level gradient information to explore the adversarial perturbation space. Comprehensive experiments on three benchmark datasets and four representative state-of-the-art models demonstrate that our proposed method significantly outperforms baselines in both white-box and black-box transfer attack scenarios under TUAP constraints. Moreover, our method also exhibits superior transfer attack performance even without TUAP constraints, demonstrating its effectiveness and superiority in generating adversarial perturbations for time series forecasting models.