SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series
This addresses the problem of making adversarial attacks more effective and less detectable for time series classification, which is incremental as it builds on existing attack methods.
The paper tackles the vulnerability of time series classification models to adversarial attacks by proposing SWAP, a method that enhances the confidence of second-ranked logits to improve attack success rates, achieving over 50% ASR and an 18% increase compared to existing methods.
Time series classification (TSC) has emerged as a critical task in various domains, and deep neural models have shown superior performance in TSC tasks. However, these models are vulnerable to adversarial attacks, where subtle perturbations can significantly impact the prediction results. Existing adversarial methods often suffer from over-parameterization or random logit perturbation, hindering their effectiveness. Additionally, increasing the attack success rate (ASR) typically involves generating more noise, making the attack more easily detectable. To address these limitations, we propose SWAP, a novel attacking method for TSC models. SWAP focuses on enhancing the confidence of the second-ranked logits while minimizing the manipulation of other logits. This is achieved by minimizing the Kullback-Leibler divergence between the target logit distribution and the predictive logit distribution. Experimental results demonstrate that SWAP achieves state-of-the-art performance, with an ASR exceeding 50% and an 18% increase compared to existing methods.