Learning to Collaborate for User-Controlled Privacy

TL;DR

This paper introduces a collaborative learning framework enabling users to control data sharing by creating sanitization functions that preserve utility while protecting privacy, demonstrated through plug-and-play and adversarial methods.

Contribution

It presents a novel collaborative approach for user-controlled privacy, allowing data sanitization without altering existing system algorithms and ensuring privacy protection even in challenging scenarios.

Findings

Sanitization functions retain utility data features.

Privacy is fully protected when users opt for it.

Framework works with existing algorithms without modification.

Abstract

It is becoming increasingly clear that users should own and control their data. Utility providers are also becoming more interested in guaranteeing data privacy. As such, users and utility providers should collaborate in data privacy, a paradigm that has not yet been developed in the privacy research community. We introduce this concept and present explicit architectures where the user controls what characteristics of the data she/he wants to share and what she/he wants to keep private. This is achieved by collaborative learning a sensitization function, either a deterministic or a stochastic one, that retains valuable information for the utility tasks but it also eliminates necessary information for the privacy ones. As illustration examples, we implement them using a plug-and-play approach, where no algorithm is changed at the system provider end, and an adversarial approach, where minor re-training of the privacy inferring engine is allowed. In both cases the learned sanitization function keeps the data in the original domain, thereby allowing the system to use the same algorithms it was using before for both original and privatized data. We show how we can maintain utility while fully protecting private information if the user chooses to do so, even when the first is harder than the second, as in the case here illustrated of identity detection while hiding gender.