Pejo, Balazs[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Tang, Qiang[Luxembourg Institute of Science & Technology - LIST]
Gergely, Biczok[Budapest University of Technology and Economics > Department of Telecommunications and Media Informatics]
Oct-2018
Yes
International
The 25th ACM Conference on Computer and Communications Security
from 15-10-2018 to 19-10-2018
Toronto
Canada
[en] Privacy ; Game Theory ; Machine Learning
[en] Machine learning algorithms have reached mainstream status and are widely deployed in many applications. The accuracy of such algorithms depends significantly on the size of the underlying training dataset; in reality a small or medium sized organization often does not have enough data to train a reasonably accurate model. For such organizations, a realistic solution is to train machine learning models based on a joint dataset (which is a union of the individual ones). Unfortunately, privacy concerns prevent them from straightforwardly doing so. While a number of privacy-preserving solutions exist for collaborating organizations to securely aggregate the parameters in the process of training the models, we are not aware of any work that provides a rational framework for the participants to precisely balance the privacy loss and accuracy gain in their collaboration. In this paper, we model the collaborative training process as a two-player game where each player aims to achieve higher accuracy while preserving the privacy of its own dataset. We introduce the notion of Price of Privacy, a novel approach for measuring the impact of privacy protection on the accuracy in the proposed framework. Furthermore, we develop a game-theoretical model for different player types, and then either find or prove the existence of a Nash Equilibrium with regard to the strength of privacy protection for each player.