Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

Ron Shmelkin, Liar Wolf, Tomer Friedlander

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021
EditorsVitomir Struc, Marija Ivanovska
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665431767
DOIs
StatePublished - 2021
Event16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021 - Virtual, Jodhpur, India
Duration: 15 Dec 202118 Dec 2021

Publication series

NameProceedings - 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021

Conference

Conference16th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2021
Country/TerritoryIndia
CityVirtual, Jodhpur
Period15/12/2118/12/21

Funding

FundersFunder number
Yandex Initiative for Machine Learning
Horizon 2020 Framework Programme
European Research Council
Horizon 2020725974

    Fingerprint

    Dive into the research topics of 'Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution'. Together they form a unique fingerprint.

    Cite this