Privacy Leakage through Innocent Content Sharing in Online Social Networks

TL;DR

This paper demonstrates that content shared across social media platforms can unintentionally reveal personal identities and locations, highlighting privacy risks through empirical case studies and a novel informativeness scoring approach.

Contribution

It introduces a method for cross-platform user de-anonymization and location inference, showing significant privacy leakage from aggregated social media content.

Findings

Cross-platform aggregation improves user identification accuracy.

Shared content can reveal user locations with high accuracy.

Active learning enhances inference performance using informative content.

Abstract

The increased popularity and ubiquitous availability of online social networks and globalised Internet access have affected the way in which people share content. The information that users willingly disclose on these platforms can be used for various purposes, from building consumer models for advertising, to inferring personal, potentially invasive, information. In this work, we use Twitter, Instagram and Foursquare data to convey the idea that the content shared by users, especially when aggregated across platforms, can potentially disclose more information than was originally intended. We perform two case studies: First, we perform user de-anonymization by mimicking the scenario of finding the identity of a user making anonymous posts within a group of users. Empirical evaluation on a sample of real-world social network profiles suggests that cross-platform aggregation introduces significant performance gains in user identification. In the second task, we show that it is possible to infer physical location visits of a user on the basis of shared Twitter and Instagram content. We present an informativeness scoring function which estimates the relevance and novelty of a shared piece of information with respect to an inference task. This measure is validated using an active learning framework which chooses the most informative content at each given point in time. Based on a large-scale data sample, we show that by doing this, we can attain an improved inference performance. In some cases this performance exceeds even the use of the user's full timeline.