<scp>BCIDS</scp>‐<scp>IoT</scp>: A Binary Classification Intrusion Detection Scheme for Internet of Things Communication

ABSTRACT The integration of Internet of Things (IoT) devices into daily life has exponentially increased the amount of data. In an IoT computing environment, like Smart Homes, Internet of Medical Things, Industrial Internet of things, Internet of Vehicles, and Smart Agriculture, there is a significant volume of data being exchanged between devices, servers, and users. This gives attackers a chance to launch malicious attacks on devices and associated resources. In this article, we have addressed this issue and proposed a machine learning‐based malware detection technique for the secure communication of IoT (BCIDS‐IoT). The proposed BCIDS‐IoT employs numerous algorithms for efficient detection. The benchmark UNSW‐NB15 dataset is utilized for the analysis. BCIDS‐IoT lowers false positives, maintains high detection rates, and allows for large‐scale network traffic without compromising performance. The various models, such as logistic regression, decision trees, random forests, extra trees, K‐nearest neighbors, and artificial neural network (ANNs), are utilized in the proposed BCIDS‐IoT. Metrics like precision, recall, and F1‐score are also calculated alongside accuracy. ANN surpassed all other models with an accuracy of . Finally, the proposed BCIDS‐IoT is also compared with different closely related schemes, indicating its outperformance among all.