SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915775275597824 |
|---|---|
| author | Bao, Zhuosen Du, Xia Lin, Zheng Zhou, Jizhe Fang, Zihan Wu, Jiening Zhang, Yuxin Chen, Zhe Pun, Chi-man Ni, Wei Luo, Jun |
| author_facet | Bao, Zhuosen Du, Xia Lin, Zheng Zhou, Jizhe Fang, Zihan Wu, Jiening Zhang, Yuxin Chen, Zhe Pun, Chi-man Ni, Wei Luo, Jun |
| contents | With the deep integration of facial recognition into online banking, identity verification, and other networked services, achieving effective decoupling of identity information from visual representations during image storage and transmission has become a critical challenge for privacy protection. To address this issue, we propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection. SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component. By leveraging semantic-guided recomposition in the latent space of a diffusion model, it generates visually anonymous adversarial faces while maintaining machine-level identity consistency. The framework incorporates momentum-driven unrestricted perturbation optimization and a semantic-visual balancing factor to synthesize multiple visually diverse, highly natural adversarial samples. Furthermore, for authorized access, the protected image can be restored to its original form when the correct password is provided. Extensive experiments on the CelebA-HQ and FFHQ datasets demonstrate that SIDeR achieves a 99% attack success rate in black-box scenarios and outperforms baseline methods by 41.28% in PSNR-based restoration quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04994 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy Bao, Zhuosen Du, Xia Lin, Zheng Zhou, Jizhe Fang, Zihan Wu, Jiening Zhang, Yuxin Chen, Zhe Pun, Chi-man Ni, Wei Luo, Jun Computer Vision and Pattern Recognition Machine Learning With the deep integration of facial recognition into online banking, identity verification, and other networked services, achieving effective decoupling of identity information from visual representations during image storage and transmission has become a critical challenge for privacy protection. To address this issue, we propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection. SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component. By leveraging semantic-guided recomposition in the latent space of a diffusion model, it generates visually anonymous adversarial faces while maintaining machine-level identity consistency. The framework incorporates momentum-driven unrestricted perturbation optimization and a semantic-visual balancing factor to synthesize multiple visually diverse, highly natural adversarial samples. Furthermore, for authorized access, the protected image can be restored to its original form when the correct password is provided. Extensive experiments on the CelebA-HQ and FFHQ datasets demonstrate that SIDeR achieves a 99% attack success rate in black-box scenarios and outperforms baseline methods by 41.28% in PSNR-based restoration quality. |
| title | SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.04994 |