Temporally Unified Adversarial Perturbations for Time Series Forecasting
This addresses a critical security vulnerability in time series forecasting models for real-world applications, though it is incremental as it builds on existing adversarial attack methods.
The paper tackles the problem of temporally inconsistent adversarial perturbations in time series forecasting by introducing Temporally Unified Adversarial Perturbations (TUAPs) and a Timestamp-wise Gradient Accumulation Method (TGAM), resulting in significant outperformance over baselines in white-box and black-box transfer attack scenarios on three benchmark datasets and four models.
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.