Clustered Approach for Clone Detection in Social Media

Abstract

With the popularity of Online Social Networks (OSN), the number of different types of digital attacks has been increased. Identity Clone Attack (ICA) is one of the leading among them that illegally uses a genuine user’s information by duplicating it in another fake profile. These attacks severely affect an identity since another malicious profile can misuse it. Hence, these clone profiles need to be identified and removed to increase the protection of users. This research introduces a novel approach to detect clone profiles on Facebook by using a clustering technique on its profile attributes and network connections. The detection process included three main stages: filter by name, cluster using weighted categorical attributes, and measure the strength of friend relationships among profiles, which follow one after another. Finally, the list of possible clones with their percentages representing the amount of duplicability to a given victim profile was presented as the model’s output. With the Agglomerative hierarchical clustering algorithm and Jaccard similarity measurement, a low-average within-cluster distance in cluster density performance and a precision of 88.75% was shown in the results. Instead of suggesting the exact clones, the duplicability percentages make this approach more practical since there are many similar profiles but not clones. This methodology increases the model’s adjustability to any other dataset as the selection of weights, thresholds, and clustering algorithm is done based on considering the distribution of the dataset.