A Survey on Differential Privacy for Unstructured Data Content

Huge amounts of unstructured data including image, video, audio, and text are ubiquitously generated and shared, and it is a challenge to protect sensitive personal information in them, such as human faces, voiceprints, and authorships. Differential privacy is the standard privacy protection technology that provides rigorous privacy guarantees for various data. This survey summarizes and analyzes differential privacy solutions to protect unstructured data content before it is shared with untrusted parties. These differential privacy methods obfuscate unstructured data after they are represented with vectors and then reconstruct them with obfuscated vectors. We summarize specific privacy models and mechanisms together with possible challenges in them. We also discuss their privacy guarantees against AI attacks and utility losses. Finally, we discuss several possible directions for future research.

Automated summary

This article summarizes and analyzes the application of differential privacy solutions in protecting unstructured data, including various privacy models and mechanisms, as well as the challenges they face. It also discusses the privacy guarantees of these methods against AI attacks and utility losses, and proposes several possible directions for future research.