Toward Face Biometric De-identification using Adversarial Examples

Mahdi Ghafourian, Julian Fierrez, Luis F. Gomez, Ruben Vera-Rodriguez, Aythami Morales, Zohra Rezgui, Raymond Veldhuis

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

1 Citation (Scopus)
7 Downloads (Pure)

Abstract

The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media. Recently, researchers turned to use adversarial examples as a countermeasure to privacy attacks. In this paper, we assess the effectiveness of using two widely known adversarial methods (BIM and ILLC) for de-identifying personal images. We discovered, unlike previous claims in the literature, that it is not easy to get a high protection success rate (suppressing identification rate) with imperceptible adversarial perturbation to the human visual system. Finally, we found out that the transferability of adversarial examples is highly affected by the training parameters of the network with which they are generated.
Original languageEnglish
Title of host publication2023 IEEE 47th Annual Computers, Software, And Applications Conference, Compsac
EditorsH Shahriar, Y Teranishi, A Cuzzocrea, M Sharmin, D Towey, AKMJA Majumder, H Kashiwazaki, JJ Yang, M Takemoto, N Sakib, R Banno, SI Ahamed
PublisherIEEE
Pages723-728
Number of pages6
ISBN (Electronic)979-8-3503-2697-0
ISBN (Print)979-8-3503-2698-7
DOIs
Publication statusPublished - 2 Aug 2023
Event2023 IEEE 47th Annual Computer Software and Applications Conference, COMPSAC 2023: Resilient Computing and Computing for Resilience in a Sustainable Cyber-Physical World - Torino, Italy
Duration: 26 Jun 202330 Jun 2023
Conference number: 47

Conference

Conference2023 IEEE 47th Annual Computer Software and Applications Conference, COMPSAC 2023
Abbreviated titleCOMPSAC
Country/TerritoryItaly
CityTorino
Period26/06/2330/06/23

Keywords

  • Adversarial Attacks
  • Artificial Intelligence
  • De-identification
  • Face Biometrics
  • 2024 OA procedure

Fingerprint

Dive into the research topics of 'Toward Face Biometric De-identification using Adversarial Examples'. Together they form a unique fingerprint.

Cite this