# Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images

## TL;DR

This paper introduces a Visual Privacy Advisor that categorizes personal information in images, predicts privacy risks, and models user-specific privacy preferences to enhance privacy protection in image sharing.

## Contribution

It presents the first comprehensive approach to predict and enforce user-specific privacy preferences directly from image content, extending privacy tools beyond explicit data.

## Key findings

- Model outperforms user judgments on privacy risk
- Dataset of 68 image attributes for privacy prediction
- User-specific privacy scores effectively enforce preferences

## Abstract

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.