Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.02096 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908610505736192 |
|---|---|
| author | Chen, Yixiao Sun, Shikun Li, Jianshu Li, Ruoyu Li, Zhe Xing, Junliang |
| author_facet | Chen, Yixiao Sun, Shikun Li, Jianshu Li, Ruoyu Li, Zhe Xing, Junliang |
| contents | Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and transferability due to their instance-agnostic nature. However, when training generators for multi-target tasks, the success rate of transfer attacks is relatively low due to the limitations of the model's capacity. To address these challenges, we propose a novel Dual-Flow framework for multi-target instance-agnostic adversarial attacks, utilizing Cascading Distribution Shift Training to develop an adversarial velocity function. Extensive experiments demonstrate that Dual-Flow significantly improves transferability over previous multi-target generative attacks. For example, it increases the success rate from Inception-v3 to ResNet-152 by 34.58\%. Furthermore, our attack method shows substantially stronger robustness against defense mechanisms, such as adversarially trained models. The code of Dual-Flow is available at: $\href{https://github.com/Chyxx/Dual-Flow}{https://github.com/Chyxx/Dual-Flow}$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02096 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization Chen, Yixiao Sun, Shikun Li, Jianshu Li, Ruoyu Li, Zhe Xing, Junliang Computer Vision and Pattern Recognition Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and transferability due to their instance-agnostic nature. However, when training generators for multi-target tasks, the success rate of transfer attacks is relatively low due to the limitations of the model's capacity. To address these challenges, we propose a novel Dual-Flow framework for multi-target instance-agnostic adversarial attacks, utilizing Cascading Distribution Shift Training to develop an adversarial velocity function. Extensive experiments demonstrate that Dual-Flow significantly improves transferability over previous multi-target generative attacks. For example, it increases the success rate from Inception-v3 to ResNet-152 by 34.58\%. Furthermore, our attack method shows substantially stronger robustness against defense mechanisms, such as adversarially trained models. The code of Dual-Flow is available at: $\href{https://github.com/Chyxx/Dual-Flow}{https://github.com/Chyxx/Dual-Flow}$. |
| title | Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.02096 |