LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914735330426880 |
|---|---|
| author | Cao, Yuxin Zhao, Ziyu Xiao, Xi Wang, Derui Xue, Minhui Lu, Jin |
| author_facet | Cao, Yuxin Zhao, Ziyu Xiao, Xi Wang, Derui Xue, Minhui Lu, Jin |
| contents | Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used in video attacks recently. In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization. We solve the first challenge by scaling down the perturbation range to a regional logo, while the second challenge is addressed by complementing an optimization stage after reinforcement learning. Experimental results substantiate the overall superiority of LogoStyleFool over three state-of-the-art patch-based attacks in terms of attack performance and semantic preservation. Meanwhile, LogoStyleFool still maintains its performance against two existing patch-based defense methods. We believe that our research is beneficial in increasing the attention of the security community to such subregional style transfer attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09935 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer Cao, Yuxin Zhao, Ziyu Xiao, Xi Wang, Derui Xue, Minhui Lu, Jin Computer Vision and Pattern Recognition Cryptography and Security Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used in video attacks recently. In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization. We solve the first challenge by scaling down the perturbation range to a regional logo, while the second challenge is addressed by complementing an optimization stage after reinforcement learning. Experimental results substantiate the overall superiority of LogoStyleFool over three state-of-the-art patch-based attacks in terms of attack performance and semantic preservation. Meanwhile, LogoStyleFool still maintains its performance against two existing patch-based defense methods. We believe that our research is beneficial in increasing the attention of the security community to such subregional style transfer attacks. |
| title | LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2312.09935 |