Subject
3 entries
Mpc
Bookmarks
Piranha: A GPU Platform for Secure Computation
Piranha (USENIX Security 2022) is a GPU platform for secure multi-party computation that exploits GPU parallelism to accelerate MPC protocols by 10-15× over CPU implementations. It shows that GPU hardware can close the practical performance gap for privacy-preserving machine learning at scale.
Secure Multiparty Computation (MPC)
Yehuda Lindell's accessible overview of secure multiparty computation (MPC) — how parties can jointly compute on private inputs without revealing them. Traces the field from Yao's two-party garbled circuits through modern practical protocols used in industry.
CrypTen: Secure Multi-Party Computation Meets Machine Learning
CrypTen is a PyTorch-compatible framework from Facebook AI Research that wraps secure multi-party computation protocols behind a familiar tensor API, making private inference and training accessible to ML practitioners without cryptography expertise. The bet is that adoption bottlenecks for privacy-preserving ML are mostly about developer experience, not theoretical limits.