SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series

TL;DR

SWAP is a new adversarial attack method for time series classification that improves success rates by focusing on second-ranked logits, making attacks more effective and less detectable.

Contribution

The paper introduces SWAP, a novel adversarial attack technique that enhances attack success by manipulating second-ranked logits, addressing limitations of previous methods.

Findings

SWAP achieves over 50% attack success rate.

It improves success rate by 18% over existing methods.

SWAP effectively reduces detectability of attacks.

Abstract

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.