Learning Privacy Preserving Encodings Through Adversarial Training
Lists
Only you see this
Abstract
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained estimator, our goal is that an estimator be unable to learn to accurately predict the private attributes even with knowledge of the encoding function. We use a natural adversarial optimization-based formulation for this-training the encoding function against a classifier for the private attribute, with both modeled as deep neural networks. The key contribution of our work is a stable and convergent optimization approach that is successful at learning an encoder with our desired properties-maintaining utility while inhibiting inference of private attributes, not just within the adversarial optimization, but also by classifiers that are trained after the encoder is fixed. We adopt a rigorous experimental protocol for verification wherein classifiers are trained exhaustively till saturation on the fixed encoders. We evaluate our approach on tasks of real-world complexity-learning high-dimensional encodings that inhibit detection of different scene categories-and find that it yields encoders that are resilient at maintaining privacy.
BibTeX
@inproceedings{pittaluga2018learning,
author = {Francesco Pittaluga and Sanjeev J. Koppal and Ayan Chakrabarti},
title = {{Learning Privacy Preserving Encodings Through Adversarial Training}},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2018},
doi = {10.1109/wacv.2019.00089},
}Loading related content...