Artificial Intelligence–Driven Adaptive Honeypots for Wireless Networks: A Comparative Survey

Wireless networks, including Wireless Sensor Networks (WSNs), Mobile Ad Hoc Networks (MANETs), Vehicular Ad Hoc Networks (VANETs), Wi-Fi, and Internet of Things (IoT) systems, play a critical role in modern communication infrastructures but remain highly vulnerable to cyberattacks due to their open medium, dynamic topology, and resource constraints. Traditional security mechanisms such as firewalls and intrusion detection systems primarily focus on prevention and detection and often fail to capture in-depth attacker behavior. Honeypots have emerged as an effective deception-based defense mechanism; however, conventional static honeypots are easily identifiable and unsuitable for dynamic wireless environments. To address these limitations, adaptive honeypots enhanced with artificial intelligence (AI) have gained increasing attention. This paper presents a comprehensive comparative survey of AI-driven adaptive honeypots for wireless networks, covering research from 2016 to 2026. The survey systematically reviews learning-based techniques, including supervised learning, unsupervised learning, and reinforcement learning, applied to honeypot configuration, deployment, and autonomous adaptation. Existing works are analyzed with respect to network domain, AI methodology, key contributions, and limitations. Furthermore, the paper highlights emerging trends such as real-time self-adaptation, generative deception, and distributed intelligence, while identifying critical research gaps related to Assistant Professor, Department of Information Technology, Karpagam Academy of Higher Education, Coimbatore.1 Assistant Professor, Department of Artificial Intelligence & Data Science, Karpagam Academy of Higher Education, Coimbatore.2 Assistant Professor, Department of Computer Science, Rathinam College of Arts and Science, Coimbatore. scalability, explainability, resource efficiency, and standardized evaluation. The survey aims to provide researchers and practitioners with a structured understanding of the state of the art and to outline promising directions for future AI-driven honeypot research in wireless networks.