SlerpFace: Face Template Protection via Spherical Linear Interpolation
This work addresses privacy risks in face recognition systems for users by defending against emerging diffusion-based inversion attacks, representing an incremental improvement over existing template protection techniques.
The paper tackles the vulnerability of face recognition templates to diffusion model attacks that can reconstruct identity-revealing face images, and proposes SlerpFace, a defense method that rotates templates to a noise-like distribution using spherical linear interpolation and feature dropout, achieving satisfactory recognition accuracy and superior protection compared to prior methods.
Contemporary face recognition systems use feature templates extracted from face images to identify persons. To enhance privacy, face template protection techniques are widely employed to conceal sensitive identity and appearance information stored in the template. This paper identifies an emerging privacy attack form utilizing diffusion models that could nullify prior protection. The attack can synthesize high-quality, identity-preserving face images from templates, revealing persons' appearance. Based on studies of the diffusion model's generative capability, this paper proposes a defense by rotating templates to a noise-like distribution. This is achieved efficiently by spherically and linearly interpolating templates on their located hypersphere. This paper further proposes to group-wisely divide and drop out templates' feature dimensions, to enhance the irreversibility of rotated templates. The proposed techniques are concretized as a novel face template protection technique, SlerpFace. Extensive experiments show that SlerpFace provides satisfactory recognition accuracy and comprehensive protection against inversion and other attack forms, superior to prior arts.