Is Face Recognition Safe from Realizable Attacks?

TL;DR

This paper demonstrates that face recognition systems are vulnerable to realistic, physically realizable attacks using subtly perturbed face images, highlighting a significant security concern.

Contribution

It introduces a novel attack method that generates realistic, subtly perturbed face images for physical attacks on black-box face recognition systems.

Findings

Subtle perturbations can successfully attack state-of-the-art systems

Realistic synthesized faces can be physically realized for attacks

Vulnerabilities exist in black-box face recognition systems

Abstract

Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition Systems are vulnerable to attacks and can lead to erroneous identification of faces. Interestingly, most of these attacks are white-box, or they are manipulating facial images in ways that are not physically realizable. In this paper, we propose an attack scheme where the attacker can generate realistic synthesized face images with subtle perturbations and physically realize that onto his face to attack black-box face recognition systems. Comprehensive experiments and analyses show that subtle perturbations realized on attackers face can create successful attacks on state-of-the-art face recognition systems in black-box settings. Our study exposes the underlying vulnerability posed by the Face Recognition Systems against realizable black-box attacks.