A system for confidential inference and model protection using secure multi-party computation /
Title
A system for confidential inference and model protection using secure multi-party computation /
Subject
Computer Science
Description
Patent Number: 202241004611, Applicant: Kapil Tiwari.
The present invention relates to probabilistic inference based on secure multi-party computation (SMPC) techniques, and more particularly to Confidential Inference and Model Protection. The present invention addresses the privacy concern of model owners and ML client, by using the confidential inference and model protection aka CoInMPro, a technique to boost privacy of model parameters and client input during ML inference without affecting accuracy by paying a marginal performance cost.
The present invention relates to probabilistic inference based on secure multi-party computation (SMPC) techniques, and more particularly to Confidential Inference and Model Protection. The present invention addresses the privacy concern of model owners and ML client, by using the confidential inference and model protection aka CoInMPro, a technique to boost privacy of model parameters and client input during ML inference without affecting accuracy by paying a marginal performance cost.
Creator
George, P Jossy.
Publisher
Intellectual Property India
Date
2022
Language
English
Type
Patent
Collection
Citation
George, P Jossy., “A system for confidential inference and model protection using secure multi-party computation /,” CHRIST (Deemed To Be University) Institutional Repository, accessed July 27, 2024, https://archives.christuniversity.in/items/show/2618.