Back to articles
Article
Volume: 34 | Article ID: MWSF-210
Image
Using a GAN to Generate Adversarial Examples to Facial Image Recognition
  DOI :  10.2352/EI.2022.34.4.MWSF-210  Published OnlineJanuary 2022
Abstract
Abstract

Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that adversarial example images can be created for recognition systems which are based on deep neural networks. These adversarial examples can be used to disrupt the utility of the images as reference examples or training data. In this work we use a Generative Adversarial Network (GAN) to create adversarial examples to deceive facial recognition and we achieve an acceptable success rate in fooling the face recognition. Our results reduce the training time for the GAN by removing the discriminator component. Furthermore, our results show knowledge distillation can be employed to drastically reduce the size of the resulting model without impacting performance indicating that our contribution could run comfortably on a smartphone.

Subject Areas :
Views 70
Downloads 18
 articleview.views 70
 articleview.downloads 18
  Cite this article 

Andrew Merrigan, Alan F. Smeaton, "Using a GAN to Generate Adversarial Examples to Facial Image Recognitionin Proc. IS&T Int’l. Symp. on Electronic Imaging: Media Watermarking, Security, and Forensics,  2022,  pp 210-1 - 210-6,  https://doi.org/10.2352/EI.2022.34.4.MWSF-210

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2022
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA