FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health

• URL: http://arxiv.org/abs/2509.14275v2
• Date: Sun, 05 Oct 2025 21:41:04 GMT
• Title: FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
• Authors: Nobin Sarwar, Shubhashis Roy Dipta,
• Abstract summary: FedMentor is a fine-tuning framework for privacy-preserving adaptation of Large Language Models in sensitive domains.<n>It integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance.<n>In experiments on three mental health datasets, we show that FedMentor improves safety over standard Federated Learning (FL) without privacy.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance. Each client (domain) applies a custom DP noise scale proportional to its data sensitivity, and the server adaptively reduces noise when utility falls below a threshold. In experiments on three mental health datasets, we show that FedMentor improves safety over standard Federated Learning (FL) without privacy, raising safe output rates by up to three points and lowering toxicity, while maintaining utility (BERTScore F1 and ROUGE-L) within 0.5% of the non-private baseline and close to the centralized upper bound. The framework scales to backbones with up to 1.7B parameters on single-GPU clients, requiring < 173 MB of communication per-round. FedMentor demonstrates a practical approach to privately fine-tune LLMs for safer deployments in healthcare and other sensitive fields.

Related papers

• Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy [10.210711754168575]
  Differential privacy offers principled protection by injecting noise so confidential information remains secure on resource-limited IoT devices.<n>We propose PrivateDFL, an explainable framework that joins hyperdimensional computing with differential privacy and keeps an auditable account of cumulative noise.<n>PrivateDFL delivers higher accuracy, lower latency, and lower energy across IID and non-IID partitions while preserving formal (epsilon, delta) guarantees and operating without a central server.
  arXiv  Detail & Related papers  (2025-09-12T20:52:41Z)
• DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models [17.265217612125905]
  DP-FedLoRA is a privacy-enhanced federated fine-tuning framework.<n>It integrates LoRA-based adaptation with differential privacy in a communication-efficient setting.<n>We show that DP-FedLoRA delivers competitive performance while offering strong privacy guarantees.
  arXiv  Detail & Related papers  (2025-09-11T02:16:34Z)
• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates [58.18162789618869]
  Federated Learning (FL) is a widely used framework for training models in a decentralized manner.<n>We propose the FedRand framework, which avoids disclosing the full set of client parameters.<n>We empirically validate that FedRand improves robustness against MIAs compared to relevant baselines.
  arXiv  Detail & Related papers  (2025-03-10T11:55:50Z)
• FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning [17.853502904387376]
  Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems.<n>We propose Federated Error Minimization (FedEM), a novel algorithm that incorporates controlled perturbations through adaptive noise injection.<n> Experimental results on benchmark datasets demonstrate that FedEM significantly reduces privacy risks and preserves model accuracy, achieving a robust balance between privacy protection and utility preservation.
  arXiv  Detail & Related papers  (2025-03-08T02:48:00Z)
• Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework [19.381425127772054]
  Federated Learning (FL) is a distributed machine learning framework that inherently allows edge devices to maintain their local training data.<n>We propose a wireless physical layer (PHY) design for OTA-FL which improves differential privacy (DP) through a decentralized, dynamic power control.<n>This adaptation showcases the flexibility and effectiveness of our design across different learning algorithms while maintaining a strong emphasis on privacy.
  arXiv  Detail & Related papers  (2024-12-05T18:27:09Z)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models [87.49293964617128]
  Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data.<n>We empirically establish that cross-client domain coverage, rather than data heterogeneity, is the pivotal factor.<n>We introduce FedDCA, an algorithm that explicitly maximizes this coverage through diversity-oriented client center selection and retrieval-based augmentation.
  arXiv  Detail & Related papers  (2024-09-30T09:34:31Z)
• Binary Federated Learning with Client-Level Differential Privacy [7.854806519515342]
  Federated learning (FL) is a privacy-preserving collaborative learning framework. Existing FL systems typically adopt Federated Average (FedAvg) as the training algorithm. We propose a communication-efficient FL training algorithm with differential privacy guarantee.
  arXiv  Detail & Related papers  (2023-08-07T06:07:04Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy [67.4471689755097]
  This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity. We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
  arXiv  Detail & Related papers  (2021-06-25T14:47:19Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

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.