Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness

TL;DR

This paper introduces a novel text-guided attention framework to improve zero-shot adversarial robustness of vision-language models like CLIP, achieving significant accuracy gains by refining attention mechanisms and incorporating complementary attention strategies.

Contribution

It proposes TGA-ZSR and Comp-TGA, innovative attention-based methods that enhance robustness and generalization of pre-trained vision-language models against adversarial attacks.

Findings

TGA-ZSR improves zero-shot robustness by 9.58%.

Comp-TGA achieves an 11.95% robustness increase.

Methods outperform state-of-the-art across 16 datasets.

Abstract

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: Local Attention Refinement Module and Global Attention Constraint Module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness. Additionally, the Global Attention Constraint Module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. However, we observe that the method occasionally focuses on irrelevant or spurious features, which can lead to suboptimal performance and undermine its robustness in certain scenarios. To overcome this limitation, we further propose a novel approach called Complementary Text-Guided Attention (Comp-TGA). This method integrates two types of foreground attention: attention guided by the class prompt and reversed attention driven by the non-class prompt. These complementary attention mechanisms allow the model to capture a more comprehensive and accurate representation of the foreground. The experiments validate that TGA-ZSR and Comp-TGA yield 9.58% and 11.95% improvements respectively, in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets.