Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Ulixes: Facial Recognition Privacy with Adversarial Machine Learning

Ulixes: Facial Recognition Privacy with Adversarial Machine Learning AbstractFacial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Proceedings on Privacy Enhancing Technologies de Gruyter

Ulixes: Facial Recognition Privacy with Adversarial Machine Learning

Download PDF
18 pages

Loading next page...
 
/lp/de-gruyter/ulixes-facial-recognition-privacy-with-adversarial-machine-learning-VE7Cm88Q4a
Publisher
de Gruyter
Copyright
© 2022 Thomas Cilloni et al., published by Sciendo
ISSN
2299-0984
eISSN
2299-0984
DOI
10.2478/popets-2022-0008
Publisher site
See Article on Publisher Site

Abstract

AbstractFacial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures.

Journal

Proceedings on Privacy Enhancing Technologies – de Gruyter

Published: Jan 1, 2022

Keywords: adversarial machine learning; facial recognition; privacy

There are no references for this article.