# Generalized Attacks on Face Verification Systems

arXiv: https://arxiv.org/abs/2309.05879 · HTML: https://mlsanity.com/paper/2309.05879/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 12 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [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)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Efficient Decision-based Black-box Adversarial Attacks on Face Recognition](https://mlsanity.com/paper/1904.04433/) (2019)
- [AdvHat: Real-world adversarial attack on ArcFace Face ID system](https://mlsanity.com/paper/1908.08705/) (2019)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [A General Framework for Adversarial Examples with Objectives](https://mlsanity.com/paper/1801.00349/) (2017)
- [Towards Transferable Adversarial Attack against Deep Face Recognition](https://mlsanity.com/paper/2004.05790/) (2020)
- [Deeply learned face representations are sparse, selective, and robust](https://mlsanity.com/paper/1412.1265/) (2014)
- [On adversarial patches: real-world attack on ArcFace-100 face recognition system](https://mlsanity.com/paper/1910.07067/) (2019)
- [Surpassing Human-Level Face Verification Performance on LFW with GaussianFace](https://mlsanity.com/paper/1404.3840/) (2014)
- [Advbox: a toolbox to generate adversarial examples that fool neural networks](https://mlsanity.com/paper/2001.05574/) (2020)
- [Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems](https://mlsanity.com/paper/2006.08376/) (2020)
- [Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution](https://mlsanity.com/paper/2108.01077/) (2021)
- [Master Face Attacks on Face Recognition Systems](https://mlsanity.com/paper/2109.03398/) (2021)
- [Universal Adversarial Spoofing Attacks against Face Recognition](https://mlsanity.com/paper/2110.00708/) (2021)
- [Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution](https://mlsanity.com/paper/2211.13964/) (2022)

## Abstract (arXiv)

Face verification (FV) using deep neural network models has made tremendous progress in recent years, surpassing human accuracy and seeing deployment in various applications such as border control and smartphone unlocking. However, FV systems are vulnerable to Adversarial Attacks, which manipulate input images to deceive these systems in ways usually unnoticeable to humans. This paper provides an in-depth study of attacks on FV systems. We introduce the DodgePersonation Attack that formulates the creation of face images that impersonate a set of given identities while avoiding being identified as any of the identities in a separate, disjoint set. A taxonomy is proposed to provide a unified view of different types of Adversarial Attacks against FV systems, including Dodging Attacks, Impersonation Attacks, and Master Face Attacks. Finally, we propose the ''One Face to Rule Them All'' Attack which implements the DodgePersonation Attack with state-of-the-art performance on a well-known scenario (Master Face Attack) and which can also be used for the new scenarios introduced in this paper. While the state-of-the-art Master Face Attack can produce a set of 9 images to cover 43.82% of the identities in their test database, with 9 images our attack can cover 57.27% to 58.5% of these identifies while giving the attacker the choice of the identity to use to create the impersonation. Moreover, the 9 generated attack images appear identical to a casual observer.