Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Sibo Wang, Jie Zhang, Zheng Yuan, Shiguang Shan• 2024

Related benchmarks

TaskDatasetResultRank
Robust Image ClassificationCIFAR-10--
68
Image ClassificationCaltech256
Accuracy (Clean)76.82
51
Image ClassificationFlowers102
Clean Accuracy56.77
49
Image ClassificationStanfordCars
Clean Accuracy48.04
40
ClassificationPCAM
Clean Accuracy56.13
39
Image ClassificationCIFAR10
Clean Accuracy82.8
37
ClassificationFGVCAircraft
Robust Accuracy2.22
30
Image ClassificationOxfordPets
Robust Accuracy2.73
27
Image ClassificationCIFAR100
Clean Accuracy52.28
27
Image ClassificationFood101
Clean Accuracy70.52
25
Showing 10 of 84 rows
...

Other info

Follow for update