PriGuard: A Semantic Approach to Detect Privacy Violations in Online Social Networks

Social network users expect the social networks that they use to preserve their privacy. Traditionally, privacy breaches have been understood as the malfunctioning of a given system. However, in online social networks, privacy breaches are not necessarily a malfunctioning of a system but a byproduct of its workings. The users are allowed to create and share content about themselves and others. When multiple entities start distributing content without a control, information can reach unintended individuals and inference can reveal more information about the user. Accordingly, this paper first categorizes the privacy violations that take place in online social networks. Our categorization yields that the privacy violations in online social networks stem from intricate interactions and detecting these violations requires semantic understanding of events. Our proposed approach is based on agent-based representation of a social network, where the agents manage users' privacy requirements by creating commitments with the system. The privacy context, including the relations among users or content types, are captured using description logic. The proposed detection algorithm performs reasoning using the description logic and commitments on a varying depths of social networks. We implement the proposed model and evaluate our approach using real-life social networks.