Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning
Hunjae "Timothy" Lee, Corey Clark
TL;DR
This work tackles the challenge of training and deploying privacy-preserving machine learning with Fully Homomorphic Encryption (FHE) without interactive decryption rounds. It introduces the Blind Evaluation Framework (BEF), a cryptographic programming paradigm that decomposes logic into binary circuits and uses blind primitives (blind comparison, blind selection, blind ordering) to execute encrypted code without revealing conditions or results. The authors implement BEF for privacy-preserving decision-tree training and prediction, showing non-interactive training on encrypted data and demonstrating competitive accuracy relative to plaintext baselines on a phishing-detection dataset, with detailed runtime analyses. BEF thus enables true outsourced computation in PPML with FHE, offering a path toward scalable, IRDE-free training and inference, while highlighting current performance and memory challenges and outlining avenues for optimization and broader applicability.
Abstract
In the domain of Privacy-Preserving Machine Learning (PPML), Fully Homomorphic Encryption (FHE) is often used for encrypted computation to allow secure and privacy-preserving outsourcing of machine learning modeling. While FHE enables encrypted arithmetic operations, execution of programmatic logic such as control structures or conditional programming have remained a challenge. As a result, progress in encrypted training of PPML with FHE has been relatively stagnant compared to encrypted inference owing to the considerably higher logical complexity required in training. In addition, prior works that have demonstrated encrypted training use Interactive Rounds of Decryption and Evaluation (IRDE), where certain operations are decrypted and evaluated in plaintext using interactive rounds between the untrusted computing party (server) and the trusted private-key owner (client). In decision tree training for example, the current state-of-the-art requires d-rounds of IRDE for tree-depth of d. To address this issue in PPML and FHE, we introduce the Blind Evaluation Framework (BEF), a cryptographically secure programming framework that enables blind, but correct, execution of programming logic without IRDE. This is achieved by deconstructing programming logic into binary circuits and binary arithmetic to find alternative representations of logical statements, and adopting them to FHE for secure logical programming. To the best of our knowledge, this is the first framework to enable both training and inference of PPML models with FHE without decryption rounds. By advancing the state-of-the-art in IRDE efficiency by eliminating IRDE entirely, BEF enables adoption of FHE in use-cases where large amounts of computing services are available without the ability to have trusted clients available to perform decryption rounds.