Social Media Investigations Using Shared Photos

In recent years, social networks (SNs) have revolutionized many aspects of society. The wide variety of available platforms meets almost every kind of users’ needs: socialization, professional connections and image sharing, to name a few. Smartphones have brought vital change in user’s behaviour towards sharing of multimedia content on online SNs. One of the noticeable behaviour is taking pictures using smartphone’s camera and sharing them with contacts through online social platforms. On the flip side, SNs have contributed to the growth of the cyber crime and one of the main aspect of social networks security is to identify fake profiles. In this paper, we present a method to verify and resolve user profiles in SNs using the images posted on them, assuming taken through user’s smartphone. Creating a sort of fingerprint of the user profile, the method is capable enough to resolve profiles in spite of the fact that the images get downgraded during the uploading/downloading process. Also, the method can compare different images belonging to different SNs without using the original images. To evaluate our method, we use three online SNs and five different smartphones. The results using real dataset, show profile verification can provide results of 96.48% and resolution of 99.49% on an average values, which shows the effectiveness of our approach.