Enhancing Soft Biometric Face Template Privacy with Mutual Information-Based Image Attacks

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

Abstract

The features learned by deep-learning based face recognition networks pose privacy risks as they encode sensitive information that could be used to infer demographic attributes. In this paper, we propose an image-based solution that enhances the soft biometric privacy of the templates generated by face recognition networks. The method uses a reliable mutual information estimation and simulates a minimization step of the mutual information between the features and the target variable. We comprehensively assess the effectiveness of our approach on the gender classification task by formulating two distinct evaluation settings: one for evaluating the performance of the approach's ability to fool a given gender classifier and another for evaluating its ability to hinder the separability of the gender distributions. We conduct an extensive analysis, considering varying levels of perturbation. We show the potential of our method as a privacy-enhancing method that preserves the verification performance as well as a strong single-step adversarial attack.
Original languageEnglish
Title of host publication2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)
PublisherIEEE
Pages1141-1149
Number of pages9
ISBN (Electronic)9798350370287
ISBN (Print)979-8-3503-7071-3
DOIs
Publication statusPublished - 16 Apr 2024
EventIEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2024 - Waikoloa, United States
Duration: 4 Jan 20248 Jan 2024

Conference

ConferenceIEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2024
Abbreviated titleWACVW 2024
Country/TerritoryUnited States
CityWaikoloa
Period4/01/248/01/24

Keywords

  • Privacy
  • Protocols
  • Perturbation methods
  • Face recognition
  • Closed box
  • Minimization
  • Reliability

Fingerprint

Dive into the research topics of 'Enhancing Soft Biometric Face Template Privacy with Mutual Information-Based Image Attacks'. Together they form a unique fingerprint.

Cite this