SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation

TL;DR

This paper introduces SA-Attack, a self-augmentation method to enhance the transferability of adversarial examples in vision-language models, addressing security vulnerabilities by improving attack effectiveness across models.

Contribution

The paper proposes a novel self-augmentation based transfer attack method that improves adversarial transferability for vision-language pre-training models.

Findings

SA-Attack significantly improves transfer attack success rates.

Experiments on Flickr30K and COCO datasets validate effectiveness.

Method enhances security assessment of VLP models.

Abstract

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in incorrect predictions. In contrast to white-box adversarial attacks, transfer attacks (where the adversary crafts adversarial examples on a white-box model to fool another black-box model) are more reflective of real-world scenarios, thus making them more meaningful for research. By summarizing and analyzing existing research, we identified two factors that can influence the efficacy of transfer attacks on VLP models: inter-modal interaction and data diversity. Based on these insights, we propose a self-augment-based transfer attack method, termed SA-Attack. Specifically, during the generation of adversarial images and adversarial texts, we apply different data augmentation methods to the image modality and text modality, respectively, with the aim of improving the adversarial transferability of the generated adversarial images and texts. Experiments conducted on the FLickr30K and COCO datasets have validated the effectiveness of our method. Our code will be available after this paper is accepted.