Preventing Personal Data Theft in Images with Adversarial ML

by   Thomas Cilloni, et al.

Facial 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. This is made simpler by modern facial recognition tools, such as FaceNet, that use encoders to generate low dimensional embeddings that can be clustered to learn previously unknown faces. In this paper, we propose a strategy to generate non-invasive noise masks to apply to facial images for a newly introduced user, yielding adversarial examples and preventing the formation of identifiable clusters in the embedding space. We demonstrate the effectiveness of our method by showing that various classification and clustering methods cannot reliably cluster the adversarial examples we generate.



There are no comments yet.


page 6


Using a GAN to Generate Adversarial Examples to Facial Image Recognition

Images posted online present a privacy concern in that they may be used ...

FoggySight: A Scheme for Facial Lookup Privacy

Advances in deep learning algorithms have enabled better-than-human perf...

Facial Attributes: Accuracy and Adversarial Robustness

Facial attributes, emerging soft biometrics, must be automatically and r...

Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models

Today's proliferation of powerful facial recognition models poses a real...

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

Facial recognition systems are increasingly deployed by private corporat...

Pixelation is NOT Done in Videos Yet

This paper introduces an algorithm to protect the privacy of individuals...

Neural Network Facial Authentication for Public Electric Vehicle Charging Station

This study is to investigate and compare the facial recognition accuracy...
This week in AI

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