PulseAugur
中
实时 01:40:45
English(EN) ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

新的 ShareLock 框架实现了针对 LLM 代理的隐蔽式多工具投毒攻击

研究人员开发了 ShareLock,一个用于针对模型上下文协议 (MCP) 的隐蔽式多工具投毒攻击的新型框架,MCP 是 LLM 驱动代理的基础。该框架利用 Shamir 的阈值方案将恶意指令作为秘密份额分布在多个工具描述中,增强了隐蔽性和容错能力。ShareLock 在实验中实现了超过 90% 的攻击成功率,在检测规避方面优于现有的单工具投毒策略。 AI

影响 这项研究突显了 LLM 代理新的安全漏洞,需要改进防御机制以应对复杂的投毒攻击。

排序理由 该集群包含一篇详细介绍新型攻击框架的研究论文。

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 →

新的 ShareLock 框架实现了针对 LLM 代理的隐蔽式多工具投毒攻击

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇详细介绍新型攻击框架的研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
138 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Liwei Liu, Tianzhu Han, Zijian Liu, Zishu Dong, Na Ruan ·

    ShareLock:一种针对MCP的隐蔽式多功能阈值投毒攻击

    arXiv:2606.27027v1 Announce Type: cross Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP ha…

  2. arXiv cs.AI TIER_1 English(EN) · Na Ruan ·

    ShareLock:一种针对MCP的隐蔽式多功能阈值投毒攻击

    With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as …