HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Model
This addresses the trilemma in terminal honeypots for cybersecurity, representing a novel application of large language models rather than an incremental improvement.
The paper tackles the problem of terminal honeypots struggling to balance flexibility, interaction depth, and deception by introducing HoneyGPT, a shell honeypot architecture based on ChatGPT. The evaluation shows it achieves better balance in baseline comparisons and captures more novel attack vectors in a three-month field evaluation.
Honeypots, as a strategic cyber-deception mechanism designed to emulate authentic interactions and bait unauthorized entities, often struggle with balancing flexibility, interaction depth, and deception. They typically fail to adapt to evolving attacker tactics, with limited engagement and information gathering. Fortunately, the emergent capabilities of large language models and innovative prompt-based engineering offer a transformative shift in honeypot technologies. This paper introduces HoneyGPT, a pioneering shell honeypot architecture based on ChatGPT, characterized by its cost-effectiveness and proactive engagement. In particular, we propose a structured prompt engineering framework that incorporates chain-of-thought tactics to improve long-term memory and robust security analytics, enhancing deception and engagement. Our evaluation of HoneyGPT comprises a baseline comparison based on a collected dataset and a three-month field evaluation. The baseline comparison demonstrates HoneyGPT's remarkable ability to strike a balance among flexibility, interaction depth, and deceptive capability. The field evaluation further validates HoneyGPT's superior performance in engaging attackers more deeply and capturing a wider array of novel attack vectors.