NSL-KDD: Cyberattack Detection in IoT Utilizing Machine Learning Approaches
Anshika Sharma, Himanshi Babbar · 2023
The Internet of Things (IoT) is a new technology that makes it easy and advantageous to share information with other gadgets across wirelessly or web networks. Yet, due to changes and advancements in the IoT environment, IoT systems are more vulnerable to cyberattacks, which may result in nefarious incursions. The effects of these incursions may result in harm to the physical and the business. It becomes more difficult for the conventional system to effectively deal with these attacks as the number of network attacks that are feasible rises. A number of machine learning (ML) approaches, including Logistic Regression (LR), Decision Tree (DT), K-nearest Neighbor (KNN), Random Forest(RF), and the Support Vector Machine(SVM), have been employed to predict and visualize attack threats in order to address the aforementioned security problems. Employing the NSL-KDD dataset, the mentioned ML approaches have been compared with regard to evaluation measures, including accuracy, precision, F1-score, and recall. The results show that the RF model has the highest accuracy rate of 99.7%, while the accuracy rates for the other models, including LR, DT, KNN, and SVM, are 88.5%, 95%, 99.3%, and 97.9% respectively.