Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks

• URL: http://arxiv.org/abs/2411.07806v1
• Date: Tue, 12 Nov 2024 14:01:08 GMT
• Title: Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks
• Authors: Tianqu Kang, Zixin Wang, Hengtao He, Jun Zhang, Shenghui Song, Khaled B. Letaief,
• Abstract summary: Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. The risk of privacy eavesdropping attacks in FedFT remains a concern, particularly in sensitive areas such as healthcare and finance. We propose a split FedFT framework with differential privacy (DP) over wireless networks.
• Score: 24.667581521367357
• License:
• Abstract: Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated learning enables parameter-efficient fine-tuning. Additionally, the split FedFT architecture partitions an FM between edge devices and a central server, reducing the necessity for complete model deployment on individual devices. However, the risk of privacy eavesdropping attacks in FedFT remains a concern, particularly in sensitive areas such as healthcare and finance. In this paper, we propose a split FedFT framework with differential privacy (DP) over wireless networks, where the inherent wireless channel noise in the uplink transmission is utilized to achieve DP guarantees without adding an extra artificial noise. We shall investigate the impact of the wireless noise on convergence performance of the proposed framework. We will also show that by updating only one of the low-rank matrices in the split FedFT with DP, the proposed method can mitigate the noise amplification effect. Simulation results will demonstrate that the proposed framework achieves higher accuracy under strict privacy budgets compared to baseline methods.

Related papers

• 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)
• Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels [24.534729104570417]
  Federated learning (FL) enables edge devices to collaboratively train machine learning models. While over-the-air model aggregation improves communication efficiency, uploading models to an edge server over wireless networks can pose privacy risks. We show that FL model communication with a multiple-antenna server amplifies privacy leakage.
  arXiv  Detail & Related papers  (2023-06-19T14:44:34Z)
• Over-the-Air Federated Averaging with Limited Power and Privacy Budgets [49.04036552090802]
  This paper studies a private over-the-air federated averaging (DP-OTA-FedAvg) system with a limited sum power budget. We aim to improve the analytical problem to minimize the gap of the DP-OTA-FedAvg coefficient to minimize privacy functions.
  arXiv  Detail & Related papers  (2023-05-05T13:56:40Z)
• Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacy [16.305837225117603]
  Federated Learning (FL) is a collaborative learning framework that enables edge devices to collaboratively learn a global model while keeping raw data locally. We propose a novel wireless FL scheme called private edge learning with spars (PFELS) to provide client-level DP guarantee with intrinsic channel noise.
  arXiv  Detail & Related papers  (2023-04-15T03:04:11Z)
• Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning [86.08285033925597]
  This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of federated learning. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude.
  arXiv  Detail & Related papers  (2023-03-07T22:52:40Z)
• 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)
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy [142.5983499872664]
  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.
  arXiv  Detail & Related papers  (2021-06-20T13:51:18Z)
• Federated Model Distillation with Noise-Free Differential Privacy [35.72801867380072]
  We propose a novel framework called FEDMD-NFDP, which applies a Noise-Free Differential Privacy (NFDP) mechanism into a federated model distillation framework. Our extensive experimental results on various datasets validate that FEDMD-NFDP can deliver comparable utility and communication efficiency.
  arXiv  Detail & Related papers  (2020-09-11T17:19:56Z)
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization [27.243322019117144]
  Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. We propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee.
  arXiv  Detail & Related papers  (2020-08-01T20:22:57Z)
• Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning [56.94644428312295]
  Wireless connectivity is instrumental in enabling federated learning (FL) Channel randomnessperturbs each worker inversions model update while multiple workers updates incur significant interference on bandwidth. In A-FADMM, all workers upload their model updates to the parameter server using a single channel via analog transmissions. This not only saves communication bandwidth, but also hides each worker's exact model update trajectory from any eavesdropper.
  arXiv  Detail & Related papers  (2020-07-03T16:31:15Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

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.