ABSTRACT
The proliferation of Internet of Things (IoT) devices, Distributed Denial of Service (DDoS) attacks have made hacking them easier. These patterns of communication are difficult to detect because they evade signature and volume detection technologies. In order to identify distributed denial of service (DDoS) assaults in IoT environments, this research presents a novel Hierarchical Adaptive Detection (HAD) approach. We evaluate the algorithm's performance on popular IoT datasets such as CICIoT2023 and ToN IoT for binary and multiclass classification tasks. HAD's resources are utilized effectively, and it maintains a low false positive rate and a high recognition rate, according to the results. This is an excellent alternative for Internet of Things devices that necessitate real-time functionality but have limited resources.
