Private inference in deep neural network

US12346830B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Nishanth Chandran · Bengaluru, IN
• Divya Gupta · Phoenix, US
• Aseem Rastogi · Fremont, US
• Rahul Sharma · Savanuru, IN
• Nishant Kumar · Sunnyvale, US
• Mayank Rathee · Panchkula, IN
• Deevashwer Rathee · Panchkula, IN

Key dates

• Filing date: Oct 30, 2020
• Grant date: Jul 1, 2025
• Expiry date: Dec 3, 2043

Classification

• Technology area (CPC Y): Emerging Cross-Sectional Technologies
• CPC primary: Y02A90/10
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

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.