Affiliation:
1. Swinburne University of Technology, Melbourne, Australia
Abstract
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.
Funder
Australian Research Council
Publisher
Association for Computing Machinery (ACM)
Subject
General Computer Science,Theoretical Computer Science
Reference122 articles.
1. Geo-indistinguishability
2. Brendan Avent, Aleksandra Korolova, David Zeber, Torgeir Hovden, and Benjamin Livshits. 2017. BLENDER: Enabling local search with a hybrid differential privacy model. In 26th USENIX Security Symposium. 747–764.
3. Private Summation in the Multi-Message Shuffle Model
Cited by
106 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献