Secure and reversible face anonymization with diffusion models
This addresses privacy and security risks in face image processing for users of computer vision systems, offering a novel solution to a known bottleneck.
The paper tackles the problem of balancing secure, high-quality face anonymization with reversibility for authorized authentication by introducing a diffusion model that integrates a secret key with latent face representations and uses a deterministic diffusion process. The method produces anonymized faces that are less visually similar to the original compared to prior work.
Face images processed by computer vision algorithms contain sensitive personal information that malicious actors can capture without consent. These privacy and security risks highlight the need for effective face anonymization methods. Current methods struggle to propose a good trade-off between a secure scheme with high-quality image generation and reversibility for later person authentication. Diffusion-based approaches produce high-quality anonymized images but lack the secret key mechanism to ensure that only authorized parties can reverse the process. In this paper, we introduce, to our knowledge, the first secure, high-quality reversible anonymization method based on a diffusion model. We propose to combine the secret key with the latent faces representation of the diffusion model. To preserve identity-irrelevant features, generation is constrained by a facial mask, maintaining high-quality images. By using a deterministic forward and backward diffusion process, our approach enforces that the original face can be recovered with the correct secret key. We also show that the proposed method produces anonymized faces that are less visually similar to the original faces, compared to other previous work.