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.

翻译：本文提出SANDMAN架构，一种利用语言智能体模拟可信人类拟像的网络欺骗系统。我们的"欺骗性智能体"作为高级网络诱饵，通过延长攻击行为观测周期，实现与攻击者的高保真交互。通过实验、测量与分析，我们论证了基于五因素人格模型的提示框架如何系统性地在大语言模型中诱导出差异化"人格"。研究结果凸显了人格驱动型语言智能体在生成多样化、拟真行为方面的可行性，最终提升网络欺骗策略的有效性。