TY - JOUR AU - Adil Mohammed AU - Shima Rashidi AU - Yusra Salih PY - 2022/08/20 Y2 - 2024/03/28 TI - Detecting Denial of Service Attacks in Internet of Things Using Software-Defined Networking and Ensemble Learning JF - Cihan University-Erbil Scientific Journal JA - cuesj VL - 6 IS - 2 SE - Research Article DO - 10.24086/cuesj.v6n2y2022.pp49-56 UR - https://journals.cihanuniversity.edu.iq/index.php/cuesj/article/view/667 AB - The Internet of Things (IoT) is a novel approach to automate connections between smart devices without involving humans. The utilization of this structure is growing, and its application range is continually expanding. We confront additional issues as the usage of these networks grows, such as the presence of attackers and combating their attacks. These networks' performance may be improved, and their development can be accelerated, with new solutions to these difficulties. A new method for improving IoT security is proposed in this research, which is based on software-based network and collaborative learning. The suggested solution divides the network domain into numerous subdomains, each with its own controller for exchanging security rules with other subdomains. All of a subnet's node traffic is routed through the subnet's control node in this topology. As a result, each controller node employs an integrated learning model to continually evaluate network traffic data and detect assaults. This learning model incorporates an artificial neural network, a decision tree, and a New Biz model that uses statistical information gathered from each data stream to identify the likely existence of assaults. NSL-KDD database data was utilised to assess the proposed method's performance, and its accuracy in identifying denial of service attacks was compared to earlier approaches. ER -