An Adaptive Privacy Policy Prediction for User Uploading Data

Abstract

An Adaptive Privacy Policy Prediction (A3P) system to support users to comprise privacy settings for their images. With the accumulative volume of images, user’s stake through social sites, sustaining privacy has become a major problem, as proven by a recent trend of publicized happenings where users unintentionally shared personal information. In such a case of incidents, the need of tools to help users control access to their shared content is superficial. Towards addressing this need, it is examined the role of social context, image content, and metadata as probable indicators of users’ privacy partialities. A two-level framework which is rendering to the user’s available history on the site, defines the best available privacy policy for the user’s images being uploaded. The solution depend on an image classification framework for image categories which may be accompanied with similar policies, and on a policy prediction algorithm to automatically generate a policy for each newly uploaded image, also according to users’ social features. Over time, the created policies will follow the evolution of users’ privacy attitude. It also provides the results of extensive evaluation which determine the efficacy of the system, with prediction accuracies.