Dormant: Defending against Pose-driven Human Image Animation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912243240665088 |
|---|---|
| author | Zhou, Jiachen Wang, Mingsi Li, Tianlin Meng, Guozhu Chen, Kai |
| author_facet | Zhou, Jiachen Wang, Mingsi Li, Tianlin Meng, Guozhu Chen, Kai |
| contents | Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely exacerbates the risk of image misuse, as attackers may use one available image to create videos involving politics, violence, and other illegal content. To counter this threat, we propose Dormant, a novel protection approach tailored to defend against pose-driven human image animation techniques. Dormant applies protective perturbation to one human image, preserving the visual similarity to the original but resulting in poor-quality video generation. The protective perturbation is optimized to induce misextraction of appearance features from the image and create incoherence among the generated video frames. Our extensive evaluation across 8 animation methods and 4 datasets demonstrates the superiority of Dormant over 6 baseline protection methods, leading to misaligned identities, visual distortions, noticeable artifacts, and inconsistent frames in the generated videos. Moreover, Dormant shows effectiveness on 6 real-world commercial services, even with fully black-box access. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14424 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dormant: Defending against Pose-driven Human Image Animation Zhou, Jiachen Wang, Mingsi Li, Tianlin Meng, Guozhu Chen, Kai Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely exacerbates the risk of image misuse, as attackers may use one available image to create videos involving politics, violence, and other illegal content. To counter this threat, we propose Dormant, a novel protection approach tailored to defend against pose-driven human image animation techniques. Dormant applies protective perturbation to one human image, preserving the visual similarity to the original but resulting in poor-quality video generation. The protective perturbation is optimized to induce misextraction of appearance features from the image and create incoherence among the generated video frames. Our extensive evaluation across 8 animation methods and 4 datasets demonstrates the superiority of Dormant over 6 baseline protection methods, leading to misaligned identities, visual distortions, noticeable artifacts, and inconsistent frames in the generated videos. Moreover, Dormant shows effectiveness on 6 real-world commercial services, even with fully black-box access. |
| title | Dormant: Defending against Pose-driven Human Image Animation |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.14424 |