Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
This work addresses privacy and identity security threats for individuals in the context of AI-generated image editing, representing a domain-specific incremental improvement over existing adversarial protection methods.
The paper tackles the problem of malicious generative editing of human portraits by proposing FaceLock, a method that optimizes adversarial perturbations to destroy biometric information, resulting in edited outputs being biometrically unrecognizable and outperforming baselines in defense against various editing attempts.
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.