提出隐私保护的参数高效微调方法，实现大模型云端训练时标签不泄露。
Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
- 基于LoRA设计多参与方分割学习框架，利用参数高效特性保护标签隐私
- 在多个NLP任务上验证，相比现有方法精度更高且性能开销更低
- 适合需要云端微调但严控数据隐私的机构或开发者使用
随着深度学习模型规模增大，许多从业者转向使用微调API。这类服务涉及客户端提供数据、服务器托管模型的双方协作。虽然便捷，但客户端数据在训练过程中存在隐私泄露风险，构成垂直联邦学习的实际场景。本文系统研究在API环境下进行大模型微调并保护标签隐私的方法。分析了主流参数高效微调技术LoRA在该场景下的隐私特性，据此提出P$^3$EFT——一种利用现有PEFT特性的多方分割学习算法，在保持较低性能损失的前提下保障隐私。我们在DeBERTa-v2-XXLarge、Flan-T5 Large和LLaMA-2 7B上，通过LoRA适配器在多种NLP任务中验证该方法。结果表明，P$^3$EFT在多参与方与双参与方设置下均优于现有隐私保护方法，且具有更高的准确率。
原文摘要 · Abstract (English)
As deep learning models become larger and more expensive, many practitioners turn to fine-tuning APIs. These web services allow fine-tuning a model between two parties: the client that provides the data, and the server that hosts the model. While convenient, these APIs raise a new concern: the data of the client is at risk of privacy breach during the training procedure. This challenge presents an important practical case of vertical federated learning, where the two parties perform parameter-efficient fine-tuning (PEFT) of a large model. In this study, we systematically search for a way to fine-tune models over an API while keeping the labels private. We analyze the privacy of LoRA, a popular approach for parameter-efficient fine-tuning when training over an API. Using this analysis, we propose P$^3$EFT, a multi-party split learning algorithm that takes advantage of existing PEFT properties to maintain privacy at a lower performance overhead. To validate our algorithm, we fine-tune DeBERTa-v2-XXLarge, Flan-T5 Large and LLaMA-2 7B using LoRA adapters on a range of NLP tasks. We find that P$^3$EFT is competitive with existing privacy-preserving methods in multi-party and two-party setups while having higher accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。