Honeypots are essential tools in cybersecurity. However, most of them (even the high-interaction ones) lack the required realism to engage and fool human attackers. This limitation makes them easily discernible, hindering their effectiveness. This work introduces a novel method to create dynamic and realistic software honeypots based on Large Language Models. Preliminary results indicate that LLMs can create credible and dynamic honeypots capable of addressing important limitations of previous honeypots, such as deterministic responses, lack of adaptability, etc. We evaluated the realism of each command by conducting an experiment with human attackers who needed to say if the answer from the honeypot was fake or not. Our proposed honeypot, called shelLM, reached an accuracy rate of 0.92.

翻译：蜜罐是网络安全中的重要工具。然而，大多数蜜罐（即使是高交互式蜜罐）缺乏吸引和欺骗人类攻击者所需的真实性。这一局限性使其易于被识别，从而降低了有效性。本研究提出了一种基于大型语言模型构建动态且真实软件蜜罐的新方法。初步结果表明，LLM能够创建可信且动态的蜜罐，解决了以往蜜罐的若干关键缺陷，例如响应确定性、缺乏适应性等。我们通过开展人类攻击者实验评估了每条命令的真实性——受试者需判断蜜罐的回复是否为伪造。实验结果证明，我们提出的名为shelLM的蜜罐准确率达到了0.92。