Analysis of Semantic Attacks in Online Social Networks

Abstract

The emergence of online social networks as an important media for communication and information dissemination during the last decade has also seen the increase in abuse of the media to spread misinformation, disinformation and propaganda. Detecting the types of semantic attacks possible in online social networks would require their accurate classification. Drawing similarities with other social computing systems like Recommender systems, this paper proposes a new taxonomy for semantic attacks in social networks. Further, we propose an algorithm which uses social network as a medium for social computing to analyse the patterns of propagation of information and identify sources of misinformation in them. We construct a new information propagation graph from the social network data and carry out k-core decomposition of the graph to isolate possible contents of misinformation and the user nodes which are involved in their propagation. We used seven different data sets obtained from 'Twitter' to validate our results. © Springer-Verlag Berlin Heidelberg 2014.