Yu Yu

PrivPy: Enabling Scalable and General Privacy-Preserving Machine Learning

2018 · arXiv (Cornell University)

We introduce PrivPy, a practical privacy-preserving collaborative computation framework, especially optimized for machine learning tasks. PrivPy provides an easy-to-use and highly compatible Python programming front-end which supports high-level array operations and different secure computation engines …

Cryptography with Auxiliary Input and Trapdoor from Constant-Noise LPN.

2016 · IACR Cryptology ePrint Archive

Dodis, Kalai and Lovett STOC 2009 initiated the study of the Learning Parity with Noise LPN problem with static exponentially hard-to-invert auxiliary input. In particular, they showed that under a new assumption called Learning Subspace …

Bicoptor: Two-round Secure Three-party Non-linear Computation without Preprocessing for Privacy-preserving Machine Learning

2022 · arXiv (Cornell University)

The overhead of non-linear functions dominates the performance of the secure multiparty computation (MPC) based privacy-preserving machine learning (PPML). This work introduces a family of novel secure three-party computation (3PC) protocols, Bicoptor, which improve the …