arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11513cs.CRcs.AI
收藏

通过随机量化和软提示实现差分隐私和通信高效的大型语言模型分拆推理

Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt

Zhejiang University, Hangzhou, China(浙江大学);University of Science and Technology of China, Anhui, China(中国科学技术大学)

Yujie Gu, Richeng Jin, Xiaoyu Ji, Yier Jin, Wenyuan Xu

AI总结:

本文提出DEL框架,通过随机量化和软提示实现差分隐私和通信高效的LLM分拆推理,有效平衡隐私与效用。

摘要:

大型语言模型(LLMs)已取得了显著的性能,并引起了广泛的研究兴趣。然而,巨大的计算需求却阻碍了在资源有限的设备上的本地部署。当前流行的LLM推理范式要求用户将查询发送给服务提供商进行处理,这引发了关键的隐私问题。现有方法提出允许用户在传输前对token嵌入进行混淆,并利用本地模型进行去噪。然而,传输token嵌入并部署本地模型可能导致过度的通信和计算开销,阻碍了实际应用。在本工作中,我们提出了DEL框架,用于实现差分隐私和通信高效的LLM分拆推理。更具体地说,提出了一个嵌入投影模块和一个具有差分隐私的随机量化机制,以在保护隐私的方式下减少通信开销。为了消除对本地模型的需求,我们在服务器端采用软提示来补偿由隐私引起的效用下降。到目前为止,这是首次利用软提示来改进LLM推理中的隐私与效用之间的权衡的工作,并且在文本生成和自然语言理解基准上的广泛实验展示了所提出方法的有效性。

英文摘要:

Large Language Models (LLMs) have achieved remarkable performance and received significant research interest. The enormous computational demands, however, hinder the local deployment on devices with limited resources. The current prevalent LLM inference paradigms require users to send queries to the service providers for processing, which raises critical privacy concerns. Existing approaches propose to allow the users to obfuscate the token embeddings before transmission and utilize local models for denoising. Nonetheless, transmitting the token embeddings and deploying local models may result in excessive communication and computation overhead, preventing practical implementation. In this work, we propose \textbf{DEL}, a framework for \textbf{D}ifferentially private and communication \textbf{E}fficient \textbf{L}LM split inference. More specifically, an embedding projection module and a differentially private stochastic quantization mechanism are proposed to reduce the communication overhead in a privacy-preserving manner. To eliminate the need for local models, we adapt soft prompt at the server side to compensate for the utility degradation caused by privacy. To the best of our knowledge, this is the first work that utilizes soft prompt to improve the trade-off between privacy and utility in LLM inference, and extensive experiments on text generation and natural language understanding benchmarks demonstrate the effectiveness of the proposed method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑