Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.01925 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909238635266048 |
|---|---|
| author | Ying, Zijian Li, Qianmu Wang, Tao Lian, Zhichao Meng, Shunmei Zhang, Xuyun |
| author_facet | Ying, Zijian Li, Qianmu Wang, Tao Lian, Zhichao Meng, Shunmei Zhang, Xuyun |
| contents | Various methods try to enhance adversarial transferability by improving the generalization from different perspectives. In this paper, we rethink the optimization process and propose a novel sequence optimization concept, which is named Looking From the Future (LFF). LFF makes use of the original optimization process to refine the very first local optimization choice. Adapting the LFF concept to the adversarial attack task, we further propose an LFF attack as well as an MLFF attack with better generalization ability. Furthermore, guiding with the LFF concept, we propose an $LLF^{\mathcal{N}}$ attack which entends the LFF attack to a multi-order attack, further enhancing the transfer attack ability. All our proposed methods can be directly applied to the iteration-based attack methods. We evaluate our proposed method on the ImageNet1k dataset by applying several SOTA adversarial attack methods under four kinds of tasks. Experimental results show that our proposed method can greatly enhance the attack transferability. Ablation experiments are also applied to verify the effectiveness of each component. The source code will be released after this paper is accepted. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01925 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability Ying, Zijian Li, Qianmu Wang, Tao Lian, Zhichao Meng, Shunmei Zhang, Xuyun Computer Vision and Pattern Recognition Various methods try to enhance adversarial transferability by improving the generalization from different perspectives. In this paper, we rethink the optimization process and propose a novel sequence optimization concept, which is named Looking From the Future (LFF). LFF makes use of the original optimization process to refine the very first local optimization choice. Adapting the LFF concept to the adversarial attack task, we further propose an LFF attack as well as an MLFF attack with better generalization ability. Furthermore, guiding with the LFF concept, we propose an $LLF^{\mathcal{N}}$ attack which entends the LFF attack to a multi-order attack, further enhancing the transfer attack ability. All our proposed methods can be directly applied to the iteration-based attack methods. We evaluate our proposed method on the ImageNet1k dataset by applying several SOTA adversarial attack methods under four kinds of tasks. Experimental results show that our proposed method can greatly enhance the attack transferability. Ablation experiments are also applied to verify the effectiveness of each component. The source code will be released after this paper is accepted. |
| title | Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.01925 |