SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jianmin, Yan, Li, Li, Borui, Yu, Lei, Shen, Chao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915810304327680
author Liu, Jianmin
Yan, Li
Li, Borui
Yu, Lei
Shen, Chao
author_facet Liu, Jianmin
Yan, Li
Li, Borui
Yu, Lei
Shen, Chao
contents Federated fine-tuning is critical for improving the performance of large language models (LLMs) in handling domain-specific tasks while keeping training data decentralized and private. However, prior work has shown that clients' private data can actually be recovered via gradient inversion attacks. Existing privacy preservation techniques against such attacks typically entail performance degradation and high costs, making them ill-suited for clients with heterogeneous data distributions and device capabilities. In this paper, we propose SHE-LoRA, which integrates selective homomorphic encryption (SHE) and low-rank adaptation (LoRA) to enable efficient and privacy-preserving federated tuning of LLMs in cross-device environments. Based on model parameter sensitivity assessment, heterogeneous clients adaptively negotiate and select a subset of model parameters for homomorphic encryption. To ensure accurate model aggregation, we design a column-aware secure aggregation method and customized reparameterization techniques to align the aggregation results with the heterogeneous device capabilities of clients. Extensive experiments demonstrate that SHE-LoRA maintains performance comparable to non-private baselines, achieves strong resistance to state-of-the-art attacks, and significantly reduces communication overhead by 99.71% and encryption time by 99.87%, compared to HE baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21051
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
Liu, Jianmin
Yan, Li
Li, Borui
Yu, Lei
Shen, Chao
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Federated fine-tuning is critical for improving the performance of large language models (LLMs) in handling domain-specific tasks while keeping training data decentralized and private. However, prior work has shown that clients' private data can actually be recovered via gradient inversion attacks. Existing privacy preservation techniques against such attacks typically entail performance degradation and high costs, making them ill-suited for clients with heterogeneous data distributions and device capabilities. In this paper, we propose SHE-LoRA, which integrates selective homomorphic encryption (SHE) and low-rank adaptation (LoRA) to enable efficient and privacy-preserving federated tuning of LLMs in cross-device environments. Based on model parameter sensitivity assessment, heterogeneous clients adaptively negotiate and select a subset of model parameters for homomorphic encryption. To ensure accurate model aggregation, we design a column-aware secure aggregation method and customized reparameterization techniques to align the aggregation results with the heterogeneous device capabilities of clients. Extensive experiments demonstrate that SHE-LoRA maintains performance comparable to non-private baselines, achieves strong resistance to state-of-the-art attacks, and significantly reduces communication overhead by 99.71% and encryption time by 99.87%, compared to HE baselines.
title SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
topic Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2505.21051