Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
- URL: http://arxiv.org/abs/2312.17493v2
- Date: Sun, 2 Jun 2024 06:31:21 GMT
- Title: Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
- Authors: Xiao-Yang Liu, Rongyi Zhu, Daochen Zha, Jiechao Gao, Shan Zhong, Matt White, Meikang Qiu,
- Abstract summary: 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.
- Score: 32.52811740662061
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science. However, concerns regarding data privacy have emerged, especially when multiple stakeholders aim to collaboratively enhance LLMs using sensitive data. In this scenario, federated learning becomes a natural choice, allowing decentralized fine-tuning without exposing raw data to central servers. Motivated by this, we investigate how data privacy can be ensured in LLM fine-tuning through practical federated learning approaches, enabling secure contributions from multiple parties to enhance LLMs. Yet, challenges arise: 1) despite avoiding raw data exposure, there is a risk of inferring sensitive information from model outputs, and 2) federated learning for LLMs incurs notable communication overhead. To address these challenges, this article introduces DP-LoRA, a novel federated learning algorithm tailored for 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. Moreover, DP-LoRA optimizes communication efficiency via low-rank adaptation, minimizing the transmission of updated weights during distributed training. The experimental results across medical, financial, and general datasets using various LLMs demonstrate that DP-LoRA effectively ensures strict privacy constraints while minimizing communication overhead.
Related papers
- 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.
Traditional frameworks like FedAvg are unsuitable for large language models (LLM)
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) - Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data [53.70870879858533]
We introduce a Federated Domain-specific Knowledge Transfer framework.
It enables domain-specific knowledge transfer from LLMs to SLMs while preserving clients' data privacy.
The proposed FDKT framework consistently and greatly improves SLMs' task performance by around 5% with a privacy budget of less than 10.
arXiv Detail & Related papers (2024-05-23T06:14:35Z) - Locally Differentially Private In-Context Learning [8.659575019965152]
Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability.
This paper proposes a locally differentially private framework of in-context learning (LDP-ICL)
Considering the mechanisms of in-context learning in Transformers by gradient descent, we provide an analysis of the trade-off between privacy and utility in such LDP-ICL.
arXiv Detail & Related papers (2024-05-07T06:05:43Z) - Personalized Wireless Federated Learning for Large Language Models [75.22457544349668]
Large Language Models (LLMs) have revolutionized natural language processing tasks.
Their deployment in wireless networks still face challenges, i.e., a lack of privacy and security protection mechanisms.
We introduce two personalized wireless federated fine-tuning methods with low communication overhead.
arXiv Detail & Related papers (2024-04-20T02:30:21Z) - FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners.
FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks.
We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
arXiv Detail & Related papers (2024-03-10T08:41:22Z) - Unmemorization in Large Language Models via Self-Distillation and
Deliberate Imagination [58.36408867180233]
Large Language Models (LLMs) struggle with crucial issues of privacy violation and unwanted exposure of sensitive data.
We introduce a novel approach termed deliberate imagination in the context of LLM unlearning.
Our results demonstrate the usefulness of this approach across different models and sizes, and also with parameter-efficient fine-tuning.
arXiv Detail & Related papers (2024-02-15T16:21:14Z) - Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN)
At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself.
This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
arXiv Detail & Related papers (2024-01-02T18:53:13Z) - Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data.
This process might suffer from privacy issues and violations of data protection regulations.
We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
arXiv Detail & Related papers (2023-10-31T03:35:59Z) - FATE-LLM: A Industrial Grade Federated Learning Framework for Large
Language Models [18.65547577691255]
Large Language Models (LLMs) have exhibited remarkable performances across various tasks in recent years.
FATE-LLM is an industrial-grade federated learning framework for large language models.
We release the code of FATE-LLM to facilitate the research of FedLLM and enable a broad range of industrial applications.
arXiv Detail & Related papers (2023-10-16T04:17:13Z) - Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy [15.145214895007134]
We propose a Secure version of the widely used Maximum Mean Discrepancy (SMMD) based on homomorphic encryption.
The proposed SMMD is able to avoid the potential information leakage in transfer learning when aligning the source and target data distribution.
arXiv Detail & Related papers (2020-09-24T13:34:32Z)
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.