VirtualIdentity: Privacy-Preserving User Profiling

TL;DR

VirtualIdentity enables social media platforms to build user profiles from content without exposing user data or proprietary models, using secure cryptographic protocols for privacy preservation.

Contribution

It introduces a novel privacy-preserving user profiling system that leverages secure multi-party cryptography to protect user data and model confidentiality.

Findings

Profiles can be accurately generated without exposing raw user data.

The system maintains the confidentiality of proprietary machine learning models.

Privacy-preserving classification achieves comparable accuracy to traditional methods.

Abstract

User profiling from user generated content (UGC) is a common practice that supports the business models of many social media companies. Existing systems require that the UGC is fully exposed to the module that constructs the user profiles. In this paper we show that it is possible to build user profiles without ever accessing the user's original data, and without exposing the trained machine learning models for user profiling -- which are the intellectual property of the company -- to the users of the social media site. We present VirtualIdentity, an application that uses secure multi-party cryptographic protocols to detect the age, gender and personality traits of users by classifying their user-generated text and personal pictures with trained support vector machine models in a privacy-preserving manner.