Confidential Inference in Decision Trees: FPGA Design and Implementation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

In confidential computing, algorithms operate on encrypted inputs to produce encrypted outputs. Specifically, in confidential inference, Alice has the parameters of the machine-learning model but does not want to reveal them to Bob who has the data. Bob wants to use Alice's model for inference but does not want to reveal his data. Alice and Bob agree to use homomorphic encryption for running the inference engine in full confidence without revealing either model or data. They find that full homomorphic encryption is very time consuming and very challenging to accelerate on hardware. In this particular case, homomorphic encryption can be made computationally efficient and can even be readily accelerated on hardware. In this paper, we reveal how Alice and Bob run the inference engine in full confidence and show an FPGA implementation of the specialized homomorphic computing algorithm they used. We further evaluate the resources needed to implement the encrypted decision tree and compare them with those of a plain decision tree. Confidential inference tests are run on the encrypted FPGA design using the MNIST dataset.

Original languageBritish English
Title of host publicationProceedings of the 2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration, VLSI-SoC 2022
PublisherIEEE Computer Society
ISBN (Electronic)9781665490054
DOIs
StatePublished - 2022
Event30th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2022 - Patras, Greece
Duration: 3 Oct 20225 Oct 2022

Publication series

NameIEEE/IFIP International Conference on VLSI and System-on-Chip, VLSI-SoC
Volume2022-October
ISSN (Print)2324-8432
ISSN (Electronic)2324-8440

Conference

Conference30th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2022
Country/TerritoryGreece
CityPatras
Period3/10/225/10/22

Fingerprint

Dive into the research topics of 'Confidential Inference in Decision Trees: FPGA Design and Implementation'. Together they form a unique fingerprint.

Cite this