Machine Learning Based Practical and Efficient DDoS Attacks Detection System for IoT
Abstract
The increasing Distributed Denial of Service (DDoS) attacks on the Internet of Things (IoT) is leading to the need for an efficient detection system. Although much research has been conducted to detect DDoS attacks on traditional networks, such as machine learning (ML) based approaches that have improved accuracy and confidence, the limited bandwidth and computation resources in IoT networks restrict the application of ML, especially deep learning (DL) based solutions that require extensive input data. In order to appropriately address the security issues in the resources-constrained IoT network, this research is aimed to reduce the input data dimensions by extracting a subset of the most relevant features from the original features and using this subset as an input to the implemented Convolutional Neural Network (CNN) model to detect DDoS attacks on IoT without degrading the detection performance. Developed a hybrid feature selection approach that uses Mutual Information (MI), Analysis of Variance (ANOVA), Chi-Squared, L1-based feature selection, and Tree-based feature selection algorithms is designed to identify important data features and reduce the data inputs needed for detection. A CNN model is implemented to test and validate the hybrid feature selection approach and to provide analysis for all selection methods. Simulation results show that detection accuracy is improved using the proposed hybrid feature selection approach. The training time is much less than the combination of each individual feature selection method. Results also show that the proposed system is practical and efficient for the detection of DDoS attacks in IoT resource-constrained environments.
Subject Area
Computer Engineering|Computer science|Artificial intelligence|Web Studies
Recommended Citation
Khadijeh Wehbi,
"Machine Learning Based Practical and Efficient DDoS Attacks Detection System for IoT"
(2022).
ETD Collection for Tennessee State University.
Paper AAI29259084.
https://digitalscholarship.tnstate.edu/dissertations/AAI29259084