公开(公告)号：US20250037072A1

公开(公告)日：2025-01-30

申请号：US18474519

申请日：2023-09-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Peeyush KUMAR ,  Ananta MUKHERJEE ,  Boling YANG ,  Nishanth CHANDRAN ,  Divya GUPTA

IPC: G06Q10/087 ,  G06F21/62

Abstract: The present disclosure relates to methods and systems that preserve privacy in a secure multi-party computation (MPC) framework in multi-agent reinforcement learning (MARL). The methods and systems use a secure MPC framework that allows for direct computation on encrypted data and enables parties to learn from others while keeping their own information private. The methods and systems provide a learning mechanism that carries out floating point operations in a privacy-preserving manner.

公开(公告)号：US20230032519A1

公开(公告)日：2023-02-02

申请号：US17085986

申请日：2020-10-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Nishanth CHANDRAN ,  Divya GUPTA ,  Aseem RASTOGI ,  Rahul SHARMA ,  Nishant KUMAR ,  Mayank RATHEE ,  Deevashwer RATHEE

IPC: G06N5/04 ,  G06N3/08 ,  H04L9/34

Abstract: A secure inference over Deep Neural Networks (DNNs) using secure two-party computation to perform privacy-preserving machine learning. The secure inference uses a particular type of comparison that can be used as a building block for various layers in the DNN including, for example, ReLU activations and divisions. The comparison securely computes a Boolean share of a bit representing whether input value x is less than input value y, where x is held by a user of the DNN, and where y is held by a provider of the DNN. Each party computing system parses their input into leaf strings of multiple bits. This is much more efficient than if the leaf strings were individual bits. Accordingly, the secure inference described herein is more readily adapted for using in complex DNNs.