PulseAugur
实时 07:41:11

LCGuard 框架增强了大型语言模型多智能体系统的安全性

研究人员开发了 LCGuard,一个旨在增强多智能体大型语言模型 (LLM) 系统安全性的新框架。该系统解决了潜在通信带来的风险,特别是通过转换器键值 (KV) 缓存,这些缓存可能在智能体之间无意中泄露敏感信息。LCGuard 通过转换 KV 缓存的伪影来降低敏感数据的可重构性,同时保留任务相关信息,从而在不显著影响性能的情况下提高安全性。 AI

影响 通过防止敏感数据通过潜在通信通道泄露,增强了基于 LLM 的多智能体系统的安全性。

排序理由 该集群包含一篇详细介绍 LLM 安全新框架的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy ·

    LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

    arXiv:2605.22786v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent comm…

  2. arXiv cs.AI TIER_1 English(EN) · Karthikeyan Natesan Ramamurthy ·

    LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

    Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-va…