A Multi-task Adversarial Attack Against Face Authentication

TL;DR

This paper introduces MTADV, a versatile multi-task adversarial attack method that effectively targets face authentication systems across various datasets, models, and attack scenarios, including single and multi-user settings.

Contribution

MTADV is the first adversarial attack algorithm capable of simultaneously addressing multiple attack scenarios in face authentication systems.

Findings

Effective against LFW, CelebA, and CelebA-HQ datasets.

Works with FaceNet, InsightFace, and CurricularFace models.

Applicable in white- and gray-box attack settings.

Abstract

Deep-learning-based identity management systems, such as face authentication systems, are vulnerable to adversarial attacks. However, existing attacks are typically designed for single-task purposes, which means they are tailored to exploit vulnerabilities unique to the individual target rather than being adaptable for multiple users or systems. This limitation makes them unsuitable for certain attack scenarios, such as morphing, universal, transferable, and counter attacks. In this paper, we propose a multi-task adversarial attack algorithm called MTADV that are adaptable for multiple users or systems. By interpreting these scenarios as multi-task attacks, MTADV is applicable to both single- and multi-task attacks, and feasible in the white- and gray-box settings. Furthermore, MTADV is effective against various face datasets, including LFW, CelebA, and CelebA-HQ, and can work with different deep learning models, such as FaceNet, InsightFace, and CurricularFace. Importantly, MTADV retains its feasibility as a single-task attack targeting a single user/system. To the best of our knowledge, MTADV is the first adversarial attack method that can target all of the aforementioned scenarios in one algorithm.