Multifaceted Privacy: Express Your Online Persona without Revealing Your Sensitive Attribute

Recent works in social network stream analysis have shown that a user's online persona attributes (e.g., location, gender, ethnicity, political interest, etc.) can be accurately inferred from the topics the user writes about or engages with. Revealing a user's sensitive attributes could represent a privacy threat to some individuals. Microtargeting (e.g., the Cambridge Analytica scandal), surveillance, and discriminating ads are examples of threats to user privacy caused by sensitive attribute inference. In this paper, we propose Multifaceted privacy, a novel privacy model that aims to obfuscate a user's sensitive attributes while publicly preserving the user's public persona. To achieve multifaceted privacy, we build Aegis, a prototype client-centric social network stream processing system that helps preserve multifaceted privacy, and thus allowing social network users to freely express their online personas without revealing their sensitive attributes of choice. Aegis continuously suggests topics and hashtags to social network users to write about in order to obfuscate their sensitive attributes and hence confuse content-based sensitive attribute inferences. Our experiments show that adding as few as 0 to 4 obfuscation posts (depending on how revealing the original post is) successfully hides a user sensitive attributes without changing the user's public persona attributes.