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

arXiv: https://arxiv.org/abs/2108.01077 · HTML: https://mlsanity.com/paper/2108.01077/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 1 Aug 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [Deep Metric Learning with Angular Loss](https://mlsanity.com/paper/1708.01682/) (2017)
- [Versatile Black-Box Optimization](https://mlsanity.com/paper/2004.14014/) (2020)
- [A Survey On Anti-Spoofing Methods For Face Recognition with RGB Cameras of Generic Consumer Devices](https://mlsanity.com/paper/2010.04145/) (2020)
- [Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems](https://mlsanity.com/paper/2006.08376/) (2020)
- [Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization](https://mlsanity.com/paper/1705.06693/) (2017)

## Built on by (most cited first, 10 of 10)

- [GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search](https://mlsanity.com/paper/2412.20953/) (2024)
- [On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations](https://mlsanity.com/paper/2203.12387/) (2022)
- [Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution](https://mlsanity.com/paper/2211.13964/) (2022)
- [Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems](https://mlsanity.com/paper/2403.12047/) (2023)
- [Reliable Detection of Doppelg"angers based on Deep Face Representations](https://mlsanity.com/paper/2201.08831/) (2022)
- [Face Verification Bypass](https://mlsanity.com/paper/2203.15068/) (2022)
- [Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage](https://mlsanity.com/paper/2209.04909/) (2022)
- [Analysis of Master Vein Attacks on Finger Vein Recognition Systems](https://mlsanity.com/paper/2210.10667/) (2022)
- [Generalized Attacks on Face Verification Systems](https://mlsanity.com/paper/2309.05879/) (2023)
- [Casting the Net! Revisiting MasterFace Impersonation Attacks](https://mlsanity.com/paper/2608.06952/) (2026)

## Abstract (arXiv)

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.