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.
@article{arxiv.2108.01077,
title = {Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution},
author = {Ron Shmelkin and Tomer Friedlander and Lior Wolf},
journal= {arXiv preprint arXiv:2108.01077},
year = {2021}
}
Comments
accepted to IEEE International Conference on Automatic Face & Gesture Recognition 2021