Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

9 October 2024

Papers citing "Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems"

2 / 2 papers shown

Title
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents Christian Schroeder de Witt AAML AI4CE 46 0 0 04 May 2025
Prompt Injection Attack to Tool Selection in LLM Agents Jiawen Shi Zenghui Yuan Guiyao Tie Pan Zhou Neil Zhenqiang Gong Lichao Sun LLMAG 51 0 0 28 Apr 2025