What type of study is this?

This is a Experimental Study study.

September 17, 2025Open Access

A practical homomorphic encryption approach for GDPR-compliant machine learning full training protocol

HLHyukki LeeKorea University JMJung-Ho MoonKorea University DYDong-Hoon YooDaejeon University

Key Points

The proposed method achieves a 1000x reduction in training time while ensuring data privacy and GDPR compliance.
Analysis on benchmark datasets confirms efficiency with minimal loss of accuracy for machine learning models.
Strategically encrypting only essential layers minimizes computational overhead in deep learning protocols.
This approach addresses critical challenges in utilizing private external datasets while maintaining performance.

Abstract

This work introduces a novel privacy-preserving full training protocol for deep learning models using external data. It addresses the critical, yet under-explored, challenge of data privacy, especially under regulations like GDPR. While homomorphic encryption has been suggested as a breakthrough for utilizing private external datasets in machine learning, naively applying it to model training from scratch is impractical due to huge computational costs. The proposed method strategically encrypts only the minimal layers required to prevent privacy breaches. This approach is carefully designed to minimize the computational overhead of homomorphic encryption, making it efficient and scalable for larger models. Comprehensive analysis on benchmark datasets (ResNet-20/110 with CIFAR-10/100) confirms compliance with GDPR requirements without significant loss of accuracy. Experiments show a 1000x reduction in training time compared to models encrypted across all layers, which is the first published benchmark as far as we know.

Demander à l'IA

Bookmark

View Full Paper