SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

• URL: http://arxiv.org/abs/2506.15307v2
• Date: Fri, 26 Sep 2025 04:13:33 GMT
• Title: SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
• Authors: Jinglong Luo, Zhuo Zhang, Yehong Zhang, Shiyu Liu, Ye Dong, Hui Wang, Yue Yu, Xun Zhou, Zenglin Xu,
• Abstract summary: Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained.<n>Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data.<n>We propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs.
• Score: 45.27141187385785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data caused by stringent privacy requirements. Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data. However, its application to LLMs has been predominantly limited to inference, as fine-tuning introduces significant efficiency challenges, particularly in backward propagation, optimizer, and self-attention operations. To address these challenges, we propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs. SecP-Tuning innovatively integrates Forward-only Tuning (FoT) through the ``data owner-server interaction" paradigm, effectively removing the need for privacy-preserving computations in backward propagation and optimization processes. Furthermore, it devises an efficient privacy-preserving Random Feature Attention (RFA), effectively mitigating the computational complexity of softmax-based self-attention and circumventing MPC-incompatible nonlinear operations. Experimental results demonstrate that, compared to full-Parameter Supervised Fine-Tuning (SFT) and gradient-based prompt tuning, SecP-Tuning achieves approximately 12 times and 16 times end-to-end acceleration, as well as 18 times and 20 times reductions in communication overhead, respectively. Moreover, in five few-shot tasks, it achieves an average performance score of 82.45, outperforming SFT's 79.90 and prompt tuning's 73.73. Additionally, the ``black-box/API-style" privacy-preserving tuning paradigm of SecP-Tuning effectively avoids memory leakage risks caused by gradient/parameter transmission.

Related papers

• Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs [2.9506547907696006]
  We introduce Randomized Masked Fine-Tuning (RMFT), a privacy-preserving fine-tuning technique that reduces memorization while minimizing performance impact.<n>We demonstrate that RMFT achieves an 80.81% reduction in Total Extraction Rate and 80.17% reduction in Seen Extraction Rate compared to baseline fine-tuning.
  arXiv  Detail & Related papers  (2025-12-02T23:46:42Z)
• FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings [23.33217268142489]
  This paper introduces the Federated Dynamic Prompt Generator (FedDPG)<n>FedDPG incorporates a dynamic prompt generator network to generate context-aware prompts based on the given input.<n>Experiments on three NLP benchmark datasets showcase that FedDPG outperforms the state-of-the-art parameter-efficient fine-tuning methods in terms of global model performance.
  arXiv  Detail & Related papers  (2025-07-22T03:47:12Z)
• SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks [17.77094760401298]
  We study the vulnerability of fine-tuned large language models to membership inference attacks (MIAs)<n>We propose SOFT, a novel defense technique that mitigates privacy leakage by leveraging influential data selection with an adjustable parameter to balance utility preservation and privacy protection.
  arXiv  Detail & Related papers  (2025-06-12T07:23:56Z)
• FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model [0.48342038441006796]
  Federated Learning (FL) offers a decentralized framework for training and fine-tuning Large Language Models (LLMs)<n>FL addresses privacy and security concerns while navigating challenges associated with the substantial computational demands of LLMs.<n>We propose a novel method, FedShield-LLM, that uses pruning with Fully Homomorphic Encryption (FHE) for Low-Rank Adaptation (LoRA) parameters.
  arXiv  Detail & Related papers  (2025-06-06T00:05:05Z)
• PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts [59.5243730853157]
  Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns.<n>Small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks.<n>We propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework to balance computational cost, performance, and privacy protection under bandwidth constraints.
  arXiv  Detail & Related papers  (2025-05-13T16:27:07Z)
• Linear-Time User-Level DP-SCO via Robust Statistics [55.350093142673316]
  User-level differentially private convex optimization (DP-SCO) has garnered significant attention due to the importance of safeguarding user privacy in machine learning applications.<n>Current methods, such as those based on differentially private gradient descent (DP-SGD), often struggle with high noise accumulation and suboptimal utility.<n>We introduce a novel linear-time algorithm that leverages robust statistics, specifically the median and trimmed mean, to overcome these challenges.
  arXiv  Detail & Related papers  (2025-02-13T02:05:45Z)
• Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning [54.20871516148981]
  We introduce the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM)<n>CEPAM achieves communication efficiency and privacy protection simultaneously.<n>We theoretically analyze the privacy guarantee of CEPAM and investigate the trade-offs among user privacy and accuracy of CEPAM.
  arXiv  Detail & Related papers  (2025-01-21T11:16:05Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• Enhancing LLMs with Smart Preprocessing for EHR Analysis [3.5839042822277585]
  Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language processing.<n>This paper introduces a compact LLM framework optimized for local deployment in environments with stringent privacy requirements.
  arXiv  Detail & Related papers  (2024-12-03T22:06:55Z)
• Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models [2.3281513013731145]
  Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. Differential Privacy (DP) offers a solution to mitigate these risks, but introduces significant computational and performance trade-offs. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage.
  arXiv  Detail & Related papers  (2024-11-24T13:17:36Z)
• FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models [14.719919025265224]
  Fine-tuning large language models (LLMs) with data from specific scenarios poses privacy leakage risks. We propose for the first time a federated discrete and transferable prompt tuning, namely FedDTPT, for black-box large language models. Our approach achieves higher accuracy, reduced communication overhead, and robustness to non-iid data in a black-box setting.
  arXiv  Detail & Related papers  (2024-11-01T19:19:23Z)
• DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction [57.83978915843095]
  This paper introduces DiSK, a novel framework designed to significantly enhance the performance of differentially private gradients.<n>To ensure practicality for large-scale training, we simplify the Kalman filtering process, minimizing its memory and computational demands.
  arXiv  Detail & Related papers  (2024-10-04T19:30:39Z)
• A Federated Framework for LLM-based Recommendation [65.12855401912948]
  Large Language Models (LLMs) have empowered generative recommendation systems through fine-tuning user behavior data.<n> utilizing the user data may pose significant privacy risks, potentially leading to ethical dilemmas and violations of data protection regulations.<n>To address the privacy concerns, Federated Learning for Recommendation (Fed4Rec) has been identified as a promising solution.
  arXiv  Detail & Related papers  (2024-02-15T14:09:28Z)
• Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models [62.838689691468666]
  We propose Federated Black-Box Prompt Tuning (Fed-BBPT) to optimally harness each local dataset. Fed-BBPT capitalizes on a central server that aids local users in collaboratively training a prompt generator through regular aggregation. Relative to extensive fine-tuning, Fed-BBPT proficiently sidesteps memory challenges tied to PTM storage and fine-tuning on local machines.
  arXiv  Detail & Related papers  (2023-10-04T19:30:49Z)
• MPCLeague: Robust MPC Platform for Privacy-Preserving Machine Learning [5.203329540700177]
  This thesis focuses on designing efficient MPC frameworks for 2, 3 and 4 parties, with at most one corruption and supports ring structures. We propose two variants for each of our frameworks, with one variant aiming to minimise the execution time while the other focuses on the monetary cost.
  arXiv  Detail & Related papers  (2021-12-26T09:25:32Z)
• Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching [91.50631418179331]
  A privacy-preserving distributed deep policy gradient (P2D3PG) is proposed to maximize the cache hit rates of devices in the MEC networks. We convert the distributed optimizations into model-free Markov decision process problems and then introduce a privacy-preserving federated learning method for popularity prediction.
  arXiv  Detail & Related papers  (2021-10-20T02:48:27Z)
• A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework [56.57225686288006]
  Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. Previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data. We propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset.
  arXiv  Detail & Related papers  (2020-03-13T23:52:03Z)

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.