Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914871614898176 |
|---|---|
| author | Wang, Jiafeng Chen, Zhaoyu Jiang, Kaixun Yang, Dingkang Hong, Lingyi Guo, Pinxue Guo, Haijing Zhang, Wenqiang |
| author_facet | Wang, Jiafeng Chen, Zhaoyu Jiang, Kaixun Yang, Dingkang Hong, Lingyi Guo, Pinxue Guo, Haijing Zhang, Wenqiang |
| contents | Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling practical black-box attacks. However, existing methods are still incapable of achieving the desired transfer attack performance. In this work, focusing on gradient optimization and consistency, we analyse the gradient elimination phenomenon as well as the local momentum optimum dilemma. To tackle these challenges, we introduce Global Momentum Initialization (GI), providing global momentum knowledge to mitigate gradient elimination. Specifically, we perform gradient pre-convergence before the attack and a global search during this stage. GI seamlessly integrates with existing transfer methods, significantly improving the success rate of transfer attacks by an average of 6.4% under various advanced defense mechanisms compared to the state-of-the-art method. Ultimately, GI demonstrates strong transferability in both image and video attack domains. Particularly, when attacking advanced defense methods in the image domain, it achieves an average attack success rate of 95.4%. The code is available at $\href{https://github.com/Omenzychen/Global-Momentum-Initialization}{https://github.com/Omenzychen/Global-Momentum-Initialization}$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_11236 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization Wang, Jiafeng Chen, Zhaoyu Jiang, Kaixun Yang, Dingkang Hong, Lingyi Guo, Pinxue Guo, Haijing Zhang, Wenqiang Computer Vision and Pattern Recognition Cryptography and Security Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling practical black-box attacks. However, existing methods are still incapable of achieving the desired transfer attack performance. In this work, focusing on gradient optimization and consistency, we analyse the gradient elimination phenomenon as well as the local momentum optimum dilemma. To tackle these challenges, we introduce Global Momentum Initialization (GI), providing global momentum knowledge to mitigate gradient elimination. Specifically, we perform gradient pre-convergence before the attack and a global search during this stage. GI seamlessly integrates with existing transfer methods, significantly improving the success rate of transfer attacks by an average of 6.4% under various advanced defense mechanisms compared to the state-of-the-art method. Ultimately, GI demonstrates strong transferability in both image and video attack domains. Particularly, when attacking advanced defense methods in the image domain, it achieves an average attack success rate of 95.4%. The code is available at $\href{https://github.com/Omenzychen/Global-Momentum-Initialization}{https://github.com/Omenzychen/Global-Momentum-Initialization}$. |
| title | Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2211.11236 |