Litcius/Paper detail

Characterizing and Optimizing End-to-End Systems for Private Inference

Karthik Garimella, Zahra Ghodsi, Nandan Kumar Jha, Siddharth Garg, Brandon Reagen

202313 citationsDOI

Abstract

In two-party machine learning prediction services, the client’s goal is to query a remote server’s trained machine learning model to perform neural network inference in some application domain. However, sensitive information can be obtained during this process by either the client or the server, leading to potential collection, unauthorized secondary use, and inappropriate access to personal information. These security concerns have given rise to Private Inference (PI), in which both the client’s personal data and the server’s trained model are kept confidential. State-of-the-art PI protocols consist of a pre-processing or offline phase and an online phase that combine several cryptographic primitives: Homomorphic Encryption (HE), Secret Sharing (SS), Garbled Circuits (GC), and Oblivious Transfer (OT). Despite the need and recent performance improvements, PI remains largely arcane today and is too slow for practical use.

Topics & Concepts

Computer scienceEnd-to-end principleInferenceComputer networkArtificial intelligenceCryptography and Data SecurityPrivacy-Preserving Technologies in DataSecurity in Wireless Sensor Networks