Published Paper Details:

The rapid expansion of Internet of Things (IoT) devices has been transformed into modern infrastructure around healthcare, industrial reformation, smart cities, and consumer applications. However, this rapid multiplication has never created security challenges, making IoT networks attractive targets for sophisticated cyberattacks [1]. Traditional signature-based intrusion detection systems (IDS) struggle to keep pace with the evolving nature of attacks, particularly botnet-based threats that exploit the inherent resource constraints of IoT devices. Deep learning has emerged as a promising solution for developing robust, adaptive intrusion detection systems capable of identifying both known and novel attack patterns in IoT environments [2]. The BoT-IoT dataset has become a critical standard for evaluating these advanced detection approaches, providing researchers with realistic network traffic data that captures the complexity of modern botnet attacks in IoT infrastructures.