Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images
This addresses privacy concerns for users sharing images online by providing a tool to automatically enforce preferences, though it is incremental as it extends existing privacy-setting concepts to visual content.
The paper tackles the problem of predicting privacy risks in images by categorizing personal information into 68 attributes and training models to predict user-specific privacy scores, with the model outperforming users' own judgments in following privacy preferences.
With an increasing number of users sharing information online, privacy implications entailing such actions are a major concern. For explicit content, such as user profile or GPS data, devices (e.g. mobile phones) as well as web services (e.g. Facebook) offer to set privacy settings in order to enforce the users' privacy preferences. We propose the first approach that extends this concept to image content in the spirit of a Visual Privacy Advisor. First, we categorize personal information in images into 68 image attributes and collect a dataset, which allows us to train models that predict such information directly from images. Second, we run a user study to understand the privacy preferences of different users w.r.t. such attributes. Third, we propose models that predict user specific privacy score from images in order to enforce the users' privacy preferences. Our model is trained to predict the user specific privacy risk and even outperforms the judgment of the users, who often fail to follow their own privacy preferences on image data.