"Identifying novel privacy issues of online users on social media platforms" by Ghazaleh Beigi and Huan Liu with Martin Vesely as coordinator
Ghazaleh Beigi, Huan Liu · ACM SIGWEB Newsletter · 2019
Online users generate tremendous amounts of data. To better serve users, it is required to share the user-related data with advertisers and application developers. Socia media user-related data might make users susceptible to unintended user privacy breach. To encourage data sharing and mitigate user privacy concerns, a number of anonymization and de-anonymization algorithms have been developed to help protect privacy of users. This article introduces our recent research on online users privacy in social media. In particular, we review an approach to identifying novel privacy issues via an adversarial attack specialized for social media data. Our work sheds light on the study of new privacy risks in social media data arising from the innate heterogeneity of user-generated data.