Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.16832 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910876436529152 |
|---|---|
| author | Wang, Hanhui Zhang, Yihua Bai, Ruizheng Zhao, Yue Liu, Sijia Tu, Zhengzhong |
| author_facet | Wang, Hanhui Zhang, Yihua Bai, Ruizheng Zhao, Yue Liu, Sijia Tu, Zhengzhong |
| contents | Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity security. Existing protection methods primarily rely on adversarial perturbations to nullify edits but often fail against diverse editing requests. We propose FaceLock, a novel approach to portrait protection that optimizes adversarial perturbations to destroy or significantly alter biometric information, rendering edited outputs biometrically unrecognizable. FaceLock integrates facial recognition and visual perception into perturbation optimization to provide robust protection against various editing attempts. We also highlight flaws in commonly used evaluation metrics and reveal how they can be manipulated, emphasizing the need for reliable assessments of protection. Experiments show FaceLock outperforms baselines in defending against malicious edits and is robust against purification techniques. Ablation studies confirm its stability and broad applicability across diffusion-based editing algorithms. Our work advances biometric defense and sets the foundation for privacy-preserving practices in image editing. The code is available at: https://github.com/taco-group/FaceLock. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16832 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing Wang, Hanhui Zhang, Yihua Bai, Ruizheng Zhao, Yue Liu, Sijia Tu, Zhengzhong Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity security. Existing protection methods primarily rely on adversarial perturbations to nullify edits but often fail against diverse editing requests. We propose FaceLock, a novel approach to portrait protection that optimizes adversarial perturbations to destroy or significantly alter biometric information, rendering edited outputs biometrically unrecognizable. FaceLock integrates facial recognition and visual perception into perturbation optimization to provide robust protection against various editing attempts. We also highlight flaws in commonly used evaluation metrics and reveal how they can be manipulated, emphasizing the need for reliable assessments of protection. Experiments show FaceLock outperforms baselines in defending against malicious edits and is robust against purification techniques. Ablation studies confirm its stability and broad applicability across diffusion-based editing algorithms. Our work advances biometric defense and sets the foundation for privacy-preserving practices in image editing. The code is available at: https://github.com/taco-group/FaceLock. |
| title | Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.16832 |