在基于LLM的蜜罐智能体中诱导个性：衡量其对类人议程生成的影响
Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation
AI总结：
本文提出SANDMAN架构，利用语言智能体模拟人类，通过五因素模型提示在LLM中诱导个性，生成多样逼真行为，提升网络欺骗效果。
摘要：
本文提出了SANDMAN，一种利用语言智能体模拟令人信服的人类模拟物的网络欺骗架构。我们的“欺骗性智能体”作为高级网络诱饵，旨在通过延长攻击行为的观察期来与攻击者进行高保真交互。通过实验、测量和分析，我们展示了基于五因素人格模型的提示模式如何系统地在大语言模型中诱导出不同的“个性”。我们的结果强调了以人物角色驱动的语言智能体在生成多样化、逼真行为方面的可行性，最终改进了网络欺骗策略。
英文摘要：
This paper presents SANDMAN, an architecture for cyber deception that leverages Language Agents to emulate convincing human simulacra. Our 'Deceptive Agents' serve as advanced cyber decoys, designed for high-fidelity engagement with attackers by extending the observation period of attack behaviours. Through experimentation, measurement, and analysis, we demonstrate how a prompt schema based on the five-factor model of personality systematically induces distinct 'personalities' in Large Language Models. Our results highlight the feasibility of persona-driven Language Agents for generating diverse, realistic behaviours, ultimately improving cyber deception strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
