Review on honeynet analysis: can LSTM and shot learning drive intelligent cyber threat modelling and automation?

Review on honeynet analysis: can LSTM and shot learning drive intelligent cyber threat modelling and automation?

연구 분야: Safety

학회: Cluster Computing

The rapid expansion of Internet of Things (IoT) devices has introduced unprecedented security challenges, making them prime targets for cyberattacks. Honeynets have emerged as a critical tool for studying attacker behavior, capturing malicious activities, and developing countermeasures. This review paper provides a comprehensive analysis of existing research on honeynets in the context of IoT security, focusing on their role in detecting and mitigating evolving threats. The paper explores the integration of advanced machine learning techniques, such as Long Short-Term Memory (LSTM) networks for temporal pattern detection and Zero-Shot Learning (ZSL) for identifying novel attacks. It also examines semantic analysis for extracting meaningful insights from network data, including packet headers, payloads, and interaction logs from honeypots like Cowrie. Furthermore, the paper highlights the growing importance of Explainable AI (XAI) in enhancing the interpretability of threat detection systems, ensuring their practical applicability in real-world scenarios. By synthesizing findings from recent studies, this review identifies key challenges, such as scalability, real-time processing, and adaptability, while outlining future directions for research. This work aims to serve as a valuable resource for researchers and practitioners seeking to advance IoT security using honeynets and machine learning technologies.