2021/08/01 by Ron Shmelkin, Shmelkin, Ron, Tomer Friedlander +3 · 3 voices
Computer Science · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #cs.CR #cs.CV #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.2108.01077
openalex publication_date 2021/08/01 · arxiv published 2021/08/01 · arxiv updated 2021/08/19 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
A master face is a face image that passes face-based identity-authentication for a large portion of the population. These faces can be used to impersonate, with a high probability of success, any user, without having access to any user-information. We optimize these faces, by using an evolutionary algorithm in the latent embedding space of the StyleGAN face generator. Multiple evolutionary strategies are compared, and we propose a novel approach that employs a neural network in order to direct the search in the direction of promising samples, without adding fitness evaluations. The results we present demonstrate that it is possible to obtain a high coverage of the LFW identities (over 40%) with less than 10 master faces, for three leading deep face recognition systems.