用提示注入反制大模型黑客，自动反击并瘫痪攻击者
Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
- 利用大模型对恶意输入的敏感性，植入误导性指令
- 实验显示对自动化攻击防御效果超95%
- 适合安全研究者与红队演练使用
大型语言模型（LLMs）正被用于自动化网络攻击，使复杂攻击更易获取且可扩展。为此，我们提出一种新型防御策略，构建了名为 Mantis 的防御框架，利用大模型对对抗性输入的脆弱性，破坏恶意操作。当检测到自动化攻击时，Mantis 会向系统响应中植入精心设计的输入，导致攻击者的 LLM 自行干扰其自身行为（被动防御），甚至可能攻陷攻击者机器（主动防御）。通过部署诱饵服务吸引攻击者，并对攻击者 LLM 实施动态提示注入，Mantis 可自主实现反向攻击。实验表明，Mantis 对自动化 LLM 驱动攻击的防御成功率持续超过 95%。为促进研究合作，Mantis 已开源：https://github.com/pasquini-dario/project_mantis
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs' susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker's LLM to disrupt their own operations (passive defense) or even compromise the attacker's machine (active defense). By deploying purposefully vulnerable decoy services to attract the attacker and using dynamic prompt injections for the attacker's LLM, Mantis can autonomously hack back the attacker. In our experiments, Mantis consistently achieved over 95% effectiveness against automated LLM-driven attacks. To foster further research and collaboration, Mantis is available as an open-source tool: https://github.com/pasquini-dario/project_mantis
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。