Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images

TL;DR

This paper introduces a new dataset and model for automatically redacting private information in images, balancing privacy protection with image utility through segmentation-based obfuscation.

Contribution

It presents the first large-scale dataset of private images with detailed annotations and a novel model for automatic privacy-preserving image redaction.

Findings

Obfuscating private regions preserves privacy while maintaining image utility.

Varying region sizes allows different privacy-utility trade-offs.

Segmentation-based redaction is effective for privacy protection.

Abstract

Images convey a broad spectrum of personal information. If such images are shared on social media platforms, this personal information is leaked which conflicts with the privacy of depicted persons. Therefore, we aim for automated approaches to redact such private information and thereby protect privacy of the individual. By conducting a user study we find that obfuscating the image regions related to the private information leads to privacy while retaining utility of the images. Moreover, by varying the size of the regions different privacy-utility trade-offs can be achieved. Our findings argue for a "redaction by segmentation" paradigm. Hence, we propose the first sizable dataset of private images "in the wild" annotated with pixel and instance level labels across a broad range of privacy classes. We present the first model for automatic redaction of diverse private information.