Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift

TL;DR

This paper introduces a self-supervised framework for generating adversarial attacks across multiple tasks in AI systems by manipulating attention maps, addressing the challenge of multi-task attack implementation.

Contribution

The paper proposes a novel Cross-Task Attack framework utilizing attention shift and self-supervision to effectively perform multi-task adversarial attacks.

Findings

Effective cross-task adversarial perturbations generated

Framework outperforms existing single-task attack methods

Validated on multiple vision tasks with strong results

Abstract

Studying adversarial attacks on artificial intelligence (AI) systems helps discover model shortcomings, enabling the construction of a more robust system. Most existing adversarial attack methods only concentrate on single-task single-model or single-task cross-model scenarios, overlooking the multi-task characteristic of artificial intelligence systems. As a result, most of the existing attacks do not pose a practical threat to a comprehensive and collaborative AI system. However, implementing cross-task attacks is highly demanding and challenging due to the difficulty in obtaining the real labels of different tasks for the same picture and harmonizing the loss functions across different tasks. To address this issue, we propose a self-supervised Cross-Task Attack framework (CTA), which utilizes co-attention and anti-attention maps to generate cross-task adversarial perturbation. Specifically, the co-attention map reflects the area to which different visual task models pay attention, while the anti-attention map reflects the area that different visual task models neglect. CTA generates cross-task perturbations by shifting the attention area of samples away from the co-attention map and closer to the anti-attention map. We conduct extensive experiments on multiple vision tasks and the experimental results confirm the effectiveness of the proposed design for adversarial attacks.