Confidential Inference in Decision Trees

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

Abstract

In confidential computing, arithmetic 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 confidential computing to run the inference engine without revealing either the model or the data. However, they find that fully homomorphic and order-preserving encryptions are very time-consuming and very challenging to accelerate on hardware. When the machine learning model is a decision tree, these encryptions 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 of a decision tree in full confidence and show FPGA implementations of additively homomorphic, order-preserving, and post-quantum order-preserving encryption on constrained hardware platforms. We further evaluate the resources needed to implement the ciphertext decision tree and compare them with those of a plaintext decision tree. Confidential inference tests are run on the encrypted FPGA design using the MNIST data set.

Original languageBritish English
Title of host publicationVLSI-SoC 2023
Subtitle of host publicationInnovations for Trustworthy Artificial Intelligence - 31st IFIP WG 10.5/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2023, Revised Extended Selected Papers
EditorsIbrahim (Abe) M. Elfadel, Lutfi Albasha
PublisherSpringer Science and Business Media Deutschland GmbH
Pages273-297
Number of pages25
ISBN (Print)9783031709463
DOIs
StatePublished - 2024
Event31st IFIP WG 10.5/IEEE International Conference on Very Large Scale Integration - System on a Chip, VLSI-SoC 2023 - Dubai, United Arab Emirates
Duration: 16 Oct 202318 Oct 2023

Publication series

NameIFIP Advances in Information and Communication Technology
Volume680 IFIPAICT
ISSN (Print)1868-4238
ISSN (Electronic)1868-422X

Conference

Conference31st IFIP WG 10.5/IEEE International Conference on Very Large Scale Integration - System on a Chip, VLSI-SoC 2023
Country/TerritoryUnited Arab Emirates
CityDubai
Period16/10/2318/10/23

Keywords

  • Combinational Circuit
  • Finite-State Machine
  • FPGA Implementation
  • Homomorphic Encryption
  • Order-Preserving Encryption
  • Post-Quantum Cryptosystem
  • Sequential Circuit

Fingerprint

Dive into the research topics of 'Confidential Inference in Decision Trees'. Together they form a unique fingerprint.

Cite this