Addressing Semantic Similarity Attacks in Online Social Networks

An efficient technique for preserving user privacy of users while publishing data is anonymization. Banks, Social Network service providers and hospitals are examples of data owners/stakeholders who anonymize their customers' data before releasing it in order to protect users' privacy. However, trustworthy information consumers still value anonymous data. Numerous anonymization models and techniques have been developed for releasing data while preserving user privacy. These models/algorithms de-identify user data, which is typically presented as graphs. Giving clear perspectives on the entire information privacy field, including recent anonymization research, tabular and SN data, is crucial. In this article, we proposed an approach for anonymization to address privacy issues in social networks specifically addressing semantic similarity attacks. Far as we are aware, our proposed technique is capable of resolving the issues of semantic similarity between sensitive attributes efficiently. The results of the proposed approach have been evaluated using the dataset of around 6000 users of a real-time social network viz. Twitter. Evaluation metrics of APL (Average Path Length) show that our technique can protect privacy and also maintain the utility of data while publishing it for public use.