Abstract: Now-a-days, the increasing volume of images users share through social networking sites, maintaining privacy has become a problem, as demonstrated by a recent wave of publicized incidents where users inadvertently shared personal information. The need of tools to help users control access to their shared content is apparent. Toward addressing this need, we propose an Adaptive Privacy Policy Prediction (A3P) system to help users privacy settings for their images. We examine the role of social context, image content, and metadata as possible indicators of users’ privacy preferences. We propose a two-level framework which according to the user’s available history on the sites, determines the best available privacy policy for the user’s images being uploaded. Our solution relies on an image classification framework for image categories which may be associated 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 generated policies will follow the evolution of users’ privacy attitude. We provide the results of our extensive evaluation over 5,000 policies, which demonstrate the effectiveness of our system, with prediction accuracies over 90 percent.

Keywords: Image processing, NLP, online information services, text mining.