多智能体大语言模型系统中，智能体通信导致秘密传播：拓扑驱动泄露与依接收者条件的脱敏
内容导读
多智能体大语言模型系统（MALS）带来了一种传统基于敏感度的防御措施未能解决的隐私泄露问题：向一名获授权智能体披露的信息，可在常规协作中传播给未获授权的智能体，而无需发生系统入侵或恶意行为。这促使人们采用拓扑感知型执行机制，在保留授权披露的同时阻止未经授权的传播。我们在协调者—工作者、点对点和层级式拓扑中评估了485个场景，采用……
对照原文
When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems
Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent can propagate through routine coordination to an unauthorized one, without compromise or malicious behavior. This motivates topology-aware enforcement that blocks unauthorized propagation while preserving authorized disclosure. We evaluate 485 scenarios across coordinator-worker, peer-to-peer, and hierarchical topologies, instru…
SOURCES · 01
相关来源
- 01arXiv · AI 文旅预印本原文
arxiv.org