This repository is a curated collection of research papers on Privacy Enhancing Technologies (PETs), primarily focusing on Differential Privacy (DP) and its applications. It serves as a valuable resource for researchers and practitioners in the fields of data privacy, machine learning, and cybersecurity.

How It Works

The repository organizes research papers by category and publication date, providing links to the papers themselves. It aims to cover various aspects of DP, including mathematical frameworks and practical implementations, with plans to expand into Multi-party Computation (MPC), Homomorphic Encryption (HE), and Trusted Execution Environment (TEE) frameworks.

Quick Start & Requirements

This is a curated list of research papers and does not involve code execution. Accessing the papers requires an internet connection. Links to official tutorials and course websites are provided for further learning.

Highlighted Details

• Extensive coverage of Differential Privacy, including theoretical frameworks and practical applications.
• Categorization of papers by topic such as Local Differential Privacy, Image Privacy, Adversarial Examples, Generative Models, Federated Learning, and Multi-Armed Bandits.
• Includes papers on related PETs like Homomorphic Encryption and Secure Multi-Party Computation.
• Provides links to relevant tutorials and course materials for deeper understanding.

Maintenance & Community

The repository is maintained by Yanqi Gu. Suggestions and pull requests are welcome.

Licensing & Compatibility

The repository itself is a collection of links to research papers. The licensing of the individual papers is determined by their respective publishers. The repository is for research purposes only.

Limitations & Caveats

This repository is a static collection of links and does not provide executable code or tools for implementing PETs. Its scope is limited to the papers that have been curated and added.