Using a GAN to Generate Adversarial Examples to Facial Image Recognition

by   Andrew Merrigan, et al.

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



There are no comments yet.


page 2

page 5


AdvFaces: Adversarial Face Synthesis

Face recognition systems have been shown to be vulnerable to adversarial...

Preventing Personal Data Theft in Images with Adversarial ML

Facial recognition tools are becoming exceptionally accurate in identify...

Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems

Thanks to recent advances in Deep Neural Networks (DNNs), face recogniti...

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer

While deep face recognition (FR) systems have shown amazing performance ...

Robustness of Facial Recognition to GAN-based Face-morphing Attacks

Face-morphing attacks have been a cause for concern for a number of year...

Improving Neural ODEs via Knowledge Distillation

Neural Ordinary Differential Equations (Neural ODEs) construct the conti...

SD-GAN: Structural and Denoising GAN reveals facial parts under occlusion

Certain facial parts are salient (unique) in appearance, which substanti...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.