Privacy-Preserving Split Learning for Federated LLM Fine-Tuning

• URL: http://arxiv.org/abs/2609.09794v1
• Date: Wed, 09 Sep 2026 06:48:21 GMT
• Title: Privacy-Preserving Split Learning for Federated LLM Fine-Tuning
• Abstract summary: Fine-tuning large language models (LLMs) on domain-specific data is essential for downstream adaptation.<n>In many deployments, a participant cannot hold the complete model locally. Split Learning (SL) addresses this by partitioning the model between the participant and a server so that only a small portion runs locally.<n> Federated Learning (FL) enables collaborative training across participants by sharing only model updates instead of raw data.
• Score: 12.651705155064102
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning large language models (LLMs) on domain-specific data is essential for downstream adaptation. In many deployments, a participant cannot hold the complete model locally. This happens because the model owner keeps the full model proprietary, or because the participant lacks sufficient compute resources. Split Learning (SL) addresses this by partitioning the model between the participant and a server so that only a small portion runs locally. When the underlying data is additionally distributed across multiple institutions with privacy requirements, Federated Learning (FL) further enables collaborative training across participants by sharing only model updates instead of raw data. In this combined setting, each client transmits intermediate activations to the server, and for LLM fine-tuning, this exchange poses an inherent privacy paradox. The autoregressive nature of LLMs causes the transmitted activations to leak the input, and existing perturbation-based defenses are fundamentally ineffective in this setting. We address this leakage through a learned obfuscate-and-recover scheme that protects participants' private datasets while still allowing an independently deployable model to be trained on the server side. Experiments demonstrate that our approach achieves strong privacy protection with modest utility loss and system overhead, making split-based federated LLM fine-tuning practically viable.

Related papers

• The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models [25.91253902620787]
  MIXGUARD is a privacy-preserving split learning framework for Large Language Models.<n> token-level obfuscation, representation-level obfuscation, and adaptive gradient mechanisms operate jointly to preserve useful learning signals.<n>We conduct experiments on four classification tasks and four text generation tasks across multiple LLM families, model sizes, architectures, and fine-tuning strategies.
  arXiv  Detail & Related papers  (2026-06-15T14:42:06Z)
• Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation [20.37072541084284]
  Federated learning (FL) enables clients to retain local data while sharing only model parameters for collaborative training.<n>We show that attackers can still extract training data from the global model, even using straightforward generation methods.<n>We introduce an enhanced attack strategy tailored to FL, which tracks global model updates during training to intensify privacy leakage.
  arXiv  Detail & Related papers  (2025-09-25T02:28:08Z)
• PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs [56.04036826558497]
  We introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE)<n>By design, PC-MoE synergistically combines the strengths of distributed computation with strong confidentiality assurances.<n>It almost matches (and sometimes exceeds) the performance and convergence rate of a fully centralized model, enjoys near 70% peak GPU RAM reduction, while being fully robust against reconstruction attacks.
  arXiv  Detail & Related papers  (2025-06-03T15:00:18Z)
• FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model [48.33280660752336]
  Large language models (LLMs) show amazing performance on many domain-specific tasks after fine-tuning with some appropriate data. Many domain-specific data are privately distributed across multiple owners. We introduce FedBiOT, a resource-efficient LLM fine-tuning approach to federated learning.
  arXiv  Detail & Related papers  (2024-06-25T16:45:47Z)
• Safely Learning with Private Data: A Federated Learning Framework for Large Language Model [3.1077263218029105]
  Federated learning (FL) is an ideal solution for training models with distributed private data.<n>Traditional frameworks like FedAvg are unsuitable for large language models (LLM)<n>We propose FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks.
  arXiv  Detail & Related papers  (2024-06-21T06:43:15Z)
• Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning [32.52811740662061]
  This article introduces DP-LoRA, a novel federated learning algorithm tailored for large language models (LLMs) DP-LoRA preserves data privacy by employing a Gaussian mechanism that adds noise in weight updates, maintaining individual data privacy while facilitating collaborative model training.
  arXiv  Detail & Related papers  (2023-12-29T06:50:38Z)
• Tunable Soft Prompts are Messengers in Federated Learning [55.924749085481544]
  Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources. The lack of model privacy protection in FL becomes an unneglectable challenge. We propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts.
  arXiv  Detail & Related papers  (2023-11-12T11:01:10Z)
• Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training [67.67045085186797]
  Almost all existing systems have to face large communication burdens if the central FL server fails. It personalizes the "right" in the deep models by alternately updating the shared and personal parameters. To further promote the shared parameters aggregation process, we propose DFed integrating the local Sharpness Miniization.
  arXiv  Detail & Related papers  (2023-05-24T13:52:18Z)
• Client-specific Property Inference against Secure Aggregation in Federated Learning [52.8564467292226]
  Federated learning has become a widely used paradigm for collaboratively training a common model among different participants. Many attacks have shown that it is still possible to infer sensitive information such as membership, property, or outright reconstruction of participant data. We show that simple linear models can effectively capture client-specific properties only from the aggregated model updates.
  arXiv  Detail & Related papers  (2023-03-07T14:11:01Z)
• Subspace based Federated Unlearning [75.90552823500633]
  Federated unlearning (FL) aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates. We propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, that lets the global model perform gradient ascent.
  arXiv  Detail & Related papers  (2023-02-24T04:29:44Z)
• Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
  Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device) In FL, each data holder trains a model locally and releases it to a central server for aggregation. In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation). In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
  arXiv  Detail & Related papers  (2022-11-20T10:49:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.