This repository serves as a comprehensive, curated collection of resources for Privacy-Preserving Machine Learning (PPML). It targets researchers, engineers, and practitioners interested in secure and private computation techniques applied to machine learning, offering a broad overview of academic papers, libraries, and frameworks in the field.

How It Works

The repository categorizes resources across key PPML areas: Secure Machine Learning (using techniques like MPC and HE), Federated Learning (including secure variants), communication optimization, and privacy leakage analysis. It lists numerous academic papers, highlighting their contributions and publication venues, providing a historical and technical overview of advancements in PPML.

Quick Start & Requirements

This is a resource list, not a runnable software project. No installation or execution commands are provided.

Highlighted Details

• Extensive bibliography of over 200 academic papers from top-tier security and machine learning conferences (e.g., S&P, USENIX Security, CCS, NeurIPS, ICML).
• Covers a wide spectrum of PPML techniques including Multi-Party Computation (MPC), Homomorphic Encryption (HE), Zero-Knowledge Proofs (ZKPs), and Federated Learning (FL).
• Lists numerous open-source libraries and frameworks such as PySyft, CrypTen, TF Encrypted, MP-SPDZ, and SEAL, facilitating practical implementation.
• Includes resources on communication optimization and analysis of privacy leakages (e.g., membership inference attacks).

Maintenance & Community

The repository appears to be a static collection of links and papers, with no explicit mention of active maintenance, contributors, or community channels.

Licensing & Compatibility

The repository itself does not host code and therefore does not have a specific software license. The linked resources likely have their own licenses.

Limitations & Caveats

As a curated list, it does not provide runnable code, benchmarks, or direct comparisons between the listed tools. The sheer volume of papers may require significant effort to navigate and evaluate for specific use cases.