A Secure Approach for Next-Generation IoT Networks

Internet of things (IoT) refers to the process of connecting intelligent devices to the internet without human intervention, these connections arrive it potential to collect new masses of data on the network, and thus new forms of knowledge. They are progressively attracting to attackers. Therefore, quite a few techniques, including authentication, encryption, data integrity and availability, have been integrated to protect IoT security. Intrusion detection systems (IDSs) are an adequate security method that able to enhanced by blending different types of algorithms such as deep learning (DL) and machine learning (ML). This paper presents a novel model with K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Random Forest (RF) algorithms using ensemble learning. The model has been evaluated on NSL-KDD. The experiments showed significant enhancements in the NSL-KDD dataset with an accuracy, a precision, a recall and f1-score around 99.9%in detecting normal activities, DDoS/DoS, Probe, R2L and U2R attacks.