Authors : Ranjan Kumar Gupta , Dr. Ranu Pandey
DOI : 10.46335/IJIES.2025.10.4.17
Article Link
Abstract – The rising cases of Distributed Denial of Service (DDoS) attacks have posed major concerns to the cybersecurity especially in the context of Internet of Things (IoT). The conventional way of detecting these attacks is failing to respond to the changing tactics of these attacks. The study discusses the use of machine learning models of classifying DDoS attacks, namely: K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Random Forest to identify the IoT data. The experiment determines the performance of these classifiers in classifying DDoS as attacks and non-attacks of the publicly available dataset. Some different performance measures, where we estimate and compare, we used can include accuracy, precision, recall, F1-score, and the Matthews Correlation Coefficient (MCC) to estimate the performance of various classifiers in finding out what was detected. The findings of this study offer a good source of information about the merits and drawbacks of each of the classifier and their subsequent use to create more productive and efficient systems of detecting DDoS attacks within the IoT environment. These results provide a reference to the subsequent choice of machine learning methods to enhance the precision and certainty of DDoS anticipation in the practice.
