用多个AI代理协作实时拦截提示注入攻击
A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
- 设计多代理协同防御系统，分步检测恶意指令
- 在400次攻击中实现0%成功率，完全阻止漏洞利用
- 适合部署在需高安全性的LLM应用中
提示注入攻击是大模型部署中的重大安全隐患，恶意输入可覆盖系统指令并引发异常行为。本文提出一种多代理防御框架，通过分工协作的LLM代理实现实时检测与阻断。评估涵盖55种不同攻击，分为8类，共400个实例，涉及ChatGLM和Llama2两个平台。无防御时，基线攻击成功率达30%（ChatGLM）和20%（Llama2）。所提多代理管道实现100%防护，将攻击成功率降至0%。系统对直接覆盖、代码执行、数据外泄及混淆攻击等各类手法均有效应对，同时保障正常查询功能。
原文摘要 · Abstract (English)
Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a novel multi-agent defense framework that employs specialized LLM agents in coordinated pipelines to detect and neutralize prompt injection attacks in real-time. We evaluate our approach using two distinct architectures: a sequential chain-of-agents pipeline and a hierarchical coordinator-based system. Our comprehensive evaluation on 55 unique prompt injection attacks, grouped into 8 categories and totaling 400 attack instances across two LLM platforms (ChatGLM and Llama2), demonstrates significant security improvements. Without defense mechanisms, baseline Attack Success Rates (ASR) reached 30% for ChatGLM and 20% for Llama2. Our multi-agent pipeline achieved 100% mitigation, reducing ASR to 0% across all tested scenarios. The framework demonstrates robustness across multiple attack categories including direct overrides, code execution attempts, data exfiltration, and obfuscation techniques, while maintaining system functionality for legitimate queries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。