Improving the Transferability of Adversarial Examples by Feature Augmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914863145549824 |
|---|---|
| author | Wang, Donghua Yao, Wen Jiang, Tingsong Zheng, Xiaohu Wu, Junqi Chen, Xiaoqian |
| author_facet | Wang, Donghua Yao, Wen Jiang, Tingsong Zheng, Xiaohu Wu, Junqi Chen, Xiaoqian |
| contents | Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across models. In this paper, we propose a simple but effective feature augmentation attack (FAUG) method, which improves adversarial transferability without introducing extra computation costs. Specifically, we inject the random noise into the intermediate features of the model to enlarge the diversity of the attack gradient, thereby mitigating the risk of overfitting to the specific model and notably amplifying adversarial transferability. Moreover, our method can be combined with existing gradient attacks to augment their performance further. Extensive experiments conducted on the ImageNet dataset across CNN and transformer models corroborate the efficacy of our method, e.g., we achieve improvement of +26.22% and +5.57% on input transformation-based attacks and combination methods, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06714 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving the Transferability of Adversarial Examples by Feature Augmentation Wang, Donghua Yao, Wen Jiang, Tingsong Zheng, Xiaohu Wu, Junqi Chen, Xiaoqian Computer Vision and Pattern Recognition Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across models. In this paper, we propose a simple but effective feature augmentation attack (FAUG) method, which improves adversarial transferability without introducing extra computation costs. Specifically, we inject the random noise into the intermediate features of the model to enlarge the diversity of the attack gradient, thereby mitigating the risk of overfitting to the specific model and notably amplifying adversarial transferability. Moreover, our method can be combined with existing gradient attacks to augment their performance further. Extensive experiments conducted on the ImageNet dataset across CNN and transformer models corroborate the efficacy of our method, e.g., we achieve improvement of +26.22% and +5.57% on input transformation-based attacks and combination methods, respectively. |
| title | Improving the Transferability of Adversarial Examples by Feature Augmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06714 |