A Pervasive, Efficient and Private Future: Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption
Khoa Nguyen, Mindaugas Budzys, Eugene Frimpong, Tanveer Khan, Antonis Michalas
TL;DR
This work proposes Hybrid Homomorphic Encryption (HHE) as a scalable path to privacy-preserving ML, introducing two PPML protocols—3PervPPML and TrustedPervPPML—that push heavy HE work to the cloud and enable edge devices to participate securely. By leveraging a BFV-based HHE scheme with the PASTA construction, the authors demonstrate reduced ciphertext sizes and overall computational/communication overhead, including a TEE-enabled variant for zero-trust scenarios. They validate the approach with a real-world ECG classification application on MIT-BIH data, showing encrypted inference can approach plaintext accuracy while CSP shoulders most of the computation, and provide detailed performance benchmarks. The results indicate that HHE-based PPML can deliver practical, private ML services across pervasive devices, balancing security guarantees with efficiency and enabling broader deployment of privacy-preserving ML in edge-centric ecosystems.
Abstract
Machine Learning (ML) has become one of the most impactful fields of data science in recent years. However, a significant concern with ML is its privacy risks due to rising attacks against ML models. Privacy-Preserving Machine Learning (PPML) methods have been proposed to mitigate the privacy and security risks of ML models. A popular approach to achieving PPML uses Homomorphic Encryption (HE). However, the highly publicized inefficiencies of HE make it unsuitable for highly scalable scenarios with resource-constrained devices. Hence, Hybrid Homomorphic Encryption (HHE) -- a modern encryption scheme that combines symmetric cryptography with HE -- has recently been introduced to overcome these challenges. HHE potentially provides a foundation to build new efficient and privacy-preserving services that transfer expensive HE operations to the cloud. This work introduces HHE to the ML field by proposing resource-friendly PPML protocols for edge devices. More precisely, we utilize HHE as the primary building block of our PPML protocols. We assess the performance of our protocols by first extensively evaluating each party's communication and computational cost on a dummy dataset and show the efficiency of our protocols by comparing them with similar protocols implemented using plain BFV. Subsequently, we demonstrate the real-world applicability of our construction by building an actual PPML application that uses HHE as its foundation to classify heart disease based on sensitive ECG data.