Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness

TL;DR

This paper introduces PMG-AFT, a novel fine-tuning method guided by pre-trained models to enhance zero-shot adversarial robustness of vision-language models like CLIP, without sacrificing generalization.

Contribution

The paper proposes a pre-trained model guided adversarial fine-tuning approach that preserves generalization features while improving robustness against adversarial attacks.

Findings

Significantly outperforms state-of-the-art methods in zero-shot robustness.

Improves clean accuracy alongside adversarial robustness.

Demonstrates effectiveness across 15 zero-shot datasets.

Abstract

Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial examples. Existing works typically employ adversarial training (fine-tuning) as a defense method against adversarial examples. However, direct application to the CLIP model may result in overfitting, compromising the model's capacity for generalization. In this paper, we propose Pre-trained Model Guided Adversarial Fine-Tuning (PMG-AFT) method, which leverages supervision from the original pre-trained model by carefully designing an auxiliary branch, to enhance the model's zero-shot adversarial robustness. Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model. Extensive Experiments on 15 zero-shot datasets demonstrate that PMG-AFT significantly outperforms the state-of-the-art method, improving the top-1 robust accuracy by an average of 4.99%. Furthermore, our approach consistently improves clean accuracy by an average of 8.72%. Our code is available at https://github.com/serendipity1122/Pre-trained-Model-Guided-Fine-Tuning-for-Zero-Shot-Adversarial-Robustness.