Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.21465 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918464265912320 |
|---|---|
| author | Luo, Junyan Yu, Peipeng Fei, Jianwei Zeng, Shiya Zhou, Xiaoyu Xia, Zhihua Liu, Xiang |
| author_facet | Luo, Junyan Yu, Peipeng Fei, Jianwei Zeng, Shiya Zhou, Xiaoyu Xia, Zhihua Liu, Xiang |
| contents | Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are ineffective against contemporary swapping models that extract robust high-level identity embeddings. We propose ID-Eraser, a feature-space proactive defense that removes identifiable facial information to prevent malicious face swapping. By injecting learnable perturbations into identity embeddings and reconstructing natural-looking protection images through a Face Revive Generator (FRG), ID-Eraser produces visually realistic results for humans while rendering the protected identities unusable for Deepfake models. Experiments show that ID-Eraser substantially disrupts identity recognition across diverse face recognition and swapping systems under strict black-box settings, achieving the lowest Top-1 accuracy (0.30) with the best FID (1.64) and LPIPS (0.020). Compared with swaps generated from clean inputs, the identity similarity of protected swaps drops sharply to an average of 0.504 across five representative face swapping models. ID-Eraser further demonstrates strong cross-dataset generalization, robustness to common distortions, and practical effectiveness on commercial APIs, reducing Tencent API similarity from 0.76 to 0.36. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21465 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation Luo, Junyan Yu, Peipeng Fei, Jianwei Zeng, Shiya Zhou, Xiaoyu Xia, Zhihua Liu, Xiang Computer Vision and Pattern Recognition Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are ineffective against contemporary swapping models that extract robust high-level identity embeddings. We propose ID-Eraser, a feature-space proactive defense that removes identifiable facial information to prevent malicious face swapping. By injecting learnable perturbations into identity embeddings and reconstructing natural-looking protection images through a Face Revive Generator (FRG), ID-Eraser produces visually realistic results for humans while rendering the protected identities unusable for Deepfake models. Experiments show that ID-Eraser substantially disrupts identity recognition across diverse face recognition and swapping systems under strict black-box settings, achieving the lowest Top-1 accuracy (0.30) with the best FID (1.64) and LPIPS (0.020). Compared with swaps generated from clean inputs, the identity similarity of protected swaps drops sharply to an average of 0.504 across five representative face swapping models. ID-Eraser further demonstrates strong cross-dataset generalization, robustness to common distortions, and practical effectiveness on commercial APIs, reducing Tencent API similarity from 0.76 to 0.36. |
| title | ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.21465 |