用代理模型分离意图与敏感计算，让大模型私密推理提速千倍。
Agentic Privacy-Preserving Machine Learning
- 用通用大模型解析用户意图，专用模型处理加密计算。
- 避免大模型直接处理密文，推理速度提升超10,000倍。
- 适合需高隐私保护的AI服务部署，如医疗、金融场景。
隐私保护机器学习（PPML）对保障AI中的数据隐私至关重要。近年来，学术界提出了多种基于密码学的可证明安全方案，但在拥有数十亿参数的大语言模型（LLMs）上，现有方法效率极低。例如，当前最先进的保密大模型推理方案比明文推理慢至少10,000倍，且随着上下文长度增加，性能差距进一步扩大。本文提出一种名为Agentic-PPML的新框架，使大模型的隐私保护推理具备实际可行性。核心思想是利用通用大模型理解用户意图，并将加密推理任务交由垂直领域训练的专用模型完成。通过将通常不包含敏感信息的语言意图解析与关键隐私计算模块化分离，该框架彻底避免了大模型直接处理加密提示，从而实现面向大模型的隐私保护服务的实际部署。
原文摘要 · Abstract (English)
Privacy-preserving machine learning (PPML) is critical to ensure data privacy in AI. Over the past few years, the community has proposed a wide range of provably secure PPML schemes that rely on various cryptography primitives. However, when it comes to large language models (LLMs) with billions of parameters, the efficiency of PPML is everything but acceptable. For instance, the state-of-the-art solution for confidential LLM inference represents at least 10,000-fold slower performance compared to plaintext inference. The performance gap is even larger when the context length increases. In this position paper, we propose a novel framework named Agentic-PPML to make PPML in LLMs practical. Our key insight is to employ a general-purpose LLM for intent understanding and delegate cryptographically secure inference to specialized models trained on vertical domains. By modularly separating language intent parsing - which typically involves little or no sensitive information - from privacy-critical computation, Agentic-PPML completely eliminates the need for the LLMs to process the encrypted prompts, enabling practical deployment of privacy-preserving LLM-centric services.
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。