SplitML: A Unified Privacy-Preserving Architecture for Federated Split-Learning in Heterogeneous Environments
Open Access
- 7 January 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 267
Abstract
While Federated Learning (FL) and Split Learning (SL) aim to uphold data confidentiality by localized training, they remain susceptible to adversarial threats such as model poisoning and sophisticated inference attacks. To mitigate these vulnerabilities, we propose , a secure and privacy-preserving framework for Federated Split Learning (FSL). By integrating secure Fully Homomorphic Encryption (FHE) with Differential Privacy (DP), establishes a defense-in-depth strategy that minimizes information leakage and thwarts reconstructive inference attempts. The framework accommodates heterogeneous model architectures by allowing clients to collaboratively train only the common top layers while keeping their bottom layers exclusive to each participant. This partitioning strategy ensures that the layers closest to the sensitive input data are never exposed to the centralized server. During the training phase, participants utilize multi-key CKKS FHE to facilitate secure weight aggregation, which ensures that no single entity can access individual updates in plaintext. For collaborative inference, clients exchange activations protected by single-key CKKS FHE to achieve a consensus derived from Total Labels (TL) or Total Predictions (TP). This consensus mechanism enhances decision reliability by aggregating decentralized insights while obfuscating soft-label confidence scores that could be exploited by attackers. Our empirical evaluation demonstrates that provides substantial defense against Membership Inference (MI) attacks, reduces temporal training costs compared to standard encrypted FL, and improves inference precision via its consensus mechanism, all while maintaining a negligible impact on federation overhead.
Keywords
All Related Versions
This publication has 88 references indexed in Scilit:
- S${}^{2}$2FL: Toward Efficient and Accurate Heterogeneous Split Federated LearningIEEE Transactions on Computers, 2025
- A Public Key Identity-Based Revocation Scheme:2024
- FedSL: Federated split learning on distributed sequential data in recurrent neural networksMultimedia Tools and Applications, 2023
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- SPEED: secure, PrivatE, and efficient deep learningMachine Learning, 2021
- Distributed learning of deep neural network over multiple agentsJournal of Network and Computer Applications, 2018
- Digital watermarking for deep neural networksInternational Journal of Multimedia Information Retrieval, 2018
- Privacy-Preserving Deep Learning via Additively Homomorphic EncryptionIEEE Transactions on Information Forensics and Security, 2017
- Fully Homomorphic Encryption without Modulus Switching from Classical GapSVP2012
- CHILD: A First Step Towards Continual LearningMachine Learning, 1997