论文研究 arXiv cs.AI Tue, 21 Jul 2026 正文 thin 4 words

PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection

英文标题:PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection

arXiv:2607.16199v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the Pl
打开原文相关 3.2 · 机会 2
media2.1 KB media640 B media612 B media380 B media9.1 KB media32.7 KB media22.8 KB media24.2 KB media34.7 KB

中文

arXiv:2607.16199v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the Pl

中文全文翻译正在补齐,可先查看下方英文原文。

English / 原文

BibTeX formatted citation

×