Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Models.

Alon Zolfi, Shai Avidan, Yuval Elovici, Asaf Shabtai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Deep learning-based facial recognition (FR) models have demonstrated state-of-the-art performance in the past few years, even when wearing protective medical face masks became commonplace during the COVID-19 pandemic. Given the outstanding performance of these models, the machine learning research community has shown increasing interest in challenging their robustness. Initially, researchers presented adversarial attacks in the digital domain, and later the attacks were transferred to the physical domain. However, in many cases, attacks in the physical domain are conspicuous, and thus may raise suspicion in real-world environments (e.g., airports). In this paper, we propose Adversarial Mask, a physical universal adversarial perturbation (UAP) against state-of-the-art FR models that is applied on face masks in the form of a carefully crafted pattern. In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets. In addition, we validated our adversarial mask’s effectiveness in real-world experiments (CCTV use case) by printing the adversarial pattern on a fabric face mask. In these experiments, the FR system was only able to identify 3.34% of the participants wearing the mask (compared to a minimum of 83.34% with other evaluated masks). A demo of our experiments can be found at: https://youtu.be/_TXkDO5z11w.
Original languageEnglish
Title of host publication Machine Learning and Knowledge Discovery in Databases ECML/PKDD (3)
EditorsMassih-Reza Amini, Stéphane Canu, Asja Fischer, Tias Guns, Petra Kralj Novak, Grigorios Tsoumakas
PublisherSpringer Cham
Pages304-320
Number of pages17
ISBN (Electronic)978-3-031-26409-2
ISBN (Print)978-3-031-26408-5
DOIs
StatePublished - 17 Mar 2022
Event22nd Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2022 - Grenoble, France
Duration: 19 Sep 202223 Sep 2022

Publication series

NameLecture Notes in Computer Science
Volume13715
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference22nd Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2022
Country/TerritoryFrance
CityGrenoble
Period19/09/2223/09/22

Keywords

  • Adversarial attack
  • Face recognition
  • Face mask

Fingerprint

Dive into the research topics of 'Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Models.'. Together they form a unique fingerprint.

Cite this