Privacy Policy Inference of User-Uploaded Images on Content Sharing Sites

Abstract

In recent years online social networking communities have undergone massive explosion. The number of sites as well as kinds of sites have grown and it allows us to communicate with a lot of people across the world. Social networking sites such as Facebook, Flickr, MySpace and LinkedIn, give opportunities to share  large  amount  of  personal  information. People upload their photos to these sites to gain public attention for social purposes, and thus many public consumer photographs are available online. The proliferation of personal data leads to privacy violation .Risks such as identify theft, embarrassment, and blackmail are faced by user’s .In order to overcome these risks flexible privacy mechanisms need to be considered. An Adaptive Privacy Policy Prediction (A3P) system helps users to compose privacy settings for their images. A two-level framework which according to the user’s available history on the site, determines the best available privacy policy for the user’s images being uploaded. A3P system aims to provide users a hassle free privacy settings experience by automatically generating personalized policies. The A3P system provides a comprehensive framework to infer privacy preferences based on the information available for a given user. .When meta data information is unavailable it is difficult to generate accurate privacy policy. Privacy violation as well as inaccurate classification will be the after effect of manual creation of meta data log information .To provide security for the information, automated annotation of images are introduced which aims to create the meta data information about the images by using K-means clustering, KNN and SIFT descriptors. It results in better security, scalability, efficiency and accuracy.