Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition

ArXi:2605.01217v1 Announce Type: new Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space perturbations to obfuscate identity information, yet their protection can degrade when adversaries learn restoration or purification mappings that partially invert the transformation.