Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network

TL;DR

This paper introduces a novel attentional adversarial attack generative network that effectively fools state-of-the-art face recognition systems by generating realistic fake faces that impersonate target individuals.

Contribution

It proposes a new generative network architecture incorporating attention and variational autoencoders, with a third player in the GAN framework for improved impersonation attacks.

Findings

Generated faces successfully evade recognition by leading face recognition models.

Most generated faces are recognized as the target person, demonstrating high attack success.

The method produces inconspicuous fake faces that mimic target identities effectively.

Abstract

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. So, it is important to study how face recognition networks are subject to attacks. In this paper, we focus on a novel way to do attacks against face recognition network that misleads the network to identify someone as the target person not misclassify inconspicuously. Simultaneously, for this purpose, we introduce a specific attentional adversarial attack generative network to generate fake face images. For capturing the semantic information of the target person, this work adds a conditional variational autoencoder and attention modules to learn the instance-level correspondences between faces. Unlike traditional two-player GAN, this work introduces face recognition networks as the third player to participate in the competition between generator and discriminator which allows the attacker to impersonate the target person better. The generated faces which are hard to arouse the notice of onlookers can evade recognition by state-of-the-art networks and most of them are recognized as the target person.