SplitAgent让企业与云端智能体协作时保护隐私，按任务类型动态调整数据脱敏程度。
SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent Collaboration
- 根据任务语义动态调整数据脱敏策略，实现隐私与效率平衡。
- 在企业场景中达成83.8%任务准确率和90.1%隐私保护水平。
- 适合处理敏感数据的企业级AI应用，如合同、财务分析等场景。
企业采用基于云的AI智能体面临根本性隐私困境：使用强大云端模型需共享敏感数据，而本地处理则受限于能力。现有框架如MCP和A2A假设完全数据共享，不适用于涉及机密信息的企业环境。本文提出SplitAgent，一种新型分布式架构，支持企业侧隐私代理与云端推理代理之间的隐私保护协作。核心创新在于上下文感知的动态去噪机制，根据任务语义自适应调整隐私保护强度——合同审查、代码审查与财务分析所需保护程度不同。SplitAgent扩展了现有智能体协议，引入差分隐私保障、零知识工具验证及隐私预算管理。在企业场景的全面实验表明，SplitAgent在保持90.1%隐私保护的同时实现83.8%的任务准确率，显著优于静态方法（73.2%准确率，79.7%隐私保护）。上下文感知去噪使任务效用提升24.1%，隐私泄露降低67%。该架构为企业在不泄露敏感数据的前提下安全采用AI提供了可行路径。
原文摘要 · Abstract (English)
Enterprise adoption of cloud-based AI agents faces a fundamental privacy dilemma: leveraging powerful cloud models requires sharing sensitive data, while local processing limits capability. Current agent frameworks like MCP and A2A assume complete data sharing, making them unsuitable for enterprise environments with confidential information. We present SplitAgent, a novel distributed architecture that enables privacy-preserving collaboration between enterprise-side privacy agents and cloud-side reasoning agents. Our key innovation is context-aware dynamic sanitization that adapts privacy protection based on task semantics -- contract review requires different sanitization than code review or financial analysis. SplitAgent extends existing agent protocols with differential privacy guarantees, zero-knowledge tool verification, and privacy budget management. Through comprehensive experiments on enterprise scenarios, we demonstrate that SplitAgent achieves 83.8\% task accuracy while maintaining 90.1\% privacy protection, significantly outperforming static approaches (73.2\% accuracy, 79.7\% privacy). Context-aware sanitization improves task utility by 24.1\% over static methods while reducing privacy leakage by 67\%. Our architecture provides a practical path for enterprise AI adoption without compromising sensitive data.
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。