Privacy Preserving Face
Privacy-preserving face recognition aims to balance the need for accurate facial identification with the protection of individual privacy. Current research focuses on developing techniques that either transform facial images to obscure visually identifiable features while retaining recognition accuracy (e.g., using frequency domain manipulation, feature subtraction, or masked autoencoders), or leverage inherently privacy-enhancing hardware like lensless cameras. These advancements are crucial for mitigating privacy risks associated with widespread face recognition deployment, impacting both the security of biometric systems and the ethical considerations surrounding facial data usage.
Papers
Reversing Deep Face Embeddings with Probable Privacy Protection
Daile Osorio-Roig, Paul A. Gerlitz, Christian Rathgeb, Christoph Busch
Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing
Daile Osorio-Roig, Mahdi Ghafourian, Christian Rathgeb, Ruben Vera-Rodriguez, Christoph Busch, Julian Fierrez
DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain
Yuxi Mi, Yuge Huang, Jiazhen Ji, Hongquan Liu, Xingkun Xu, Shouhong Ding, Shuigeng Zhou
Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
Jiazhen Ji, Huan Wang, Yuge Huang, Jiaxiang Wu, Xingkun Xu, Shouhong Ding, ShengChuan Zhang, Liujuan Cao, Rongrong Ji