Anomaly Based Network Intrusion Detection for IoT Attacks using Convolution Neural Network

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 d...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE 7th International conference for Convergence in Technology (I2CT) pp. 1 - 6
Main Authors Sharma, Bhawana, Sharma, Lokesh, Lal, Chhagan
Format Conference Proceeding
LanguageEnglish
Published IEEE 07.04.2022
Subjects
CNN
Convolution
Deep learning
DNN
HIDS
Intrusion Detection System
Measurement
Network intrusion detection
Network security
Neural networks
NIDS
Runtime
SVM
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.1109/I2CT54291.2022.9824229