Anomaly Based Network Intrusion Detection for IoT Attacks using Convolution Neural Network
Bhawana Sharma (Manipal University Jaipur)
Lokesh Sharma (Manipal University Jaipur)
C. Lal (TU Delft - Cyber Security)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
IoT is widely used in many fields, and with the expansion of the network and increment of devices, there is the dynamic growth of data in IoT systems, making the system more vulnerable to various attacks. Nowadays, network security is the primary issue in IoT, and there is a need for the system to detect intruders. In this paper, we constructed a deep learning CNN model for NIDS and utilized the NSL-KDD benchmark dataset, consisting of four attack classes, for evaluating the model’s performance. We applied the filter method for feature reduction where highly correlated features are dropped. Our 2D-CNN model achieved an accuracy of 99.4% with reduced loss. We also compared the performance of DNN and CNN models in terms of accuracy and other evaluation metrics.