.png){kind=icon}
返回
Ensemble Detection Model for IoT IDS
.png){kind=icon}
PRE
AI
DOI：10.1016/j.iot.2021.100435.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The constant development of interrelated computing devices and the emergence of new network technologies have dramatically increased the Internet of Things (IoT) devices. Intrusion Detection Systems (IDSs) play a significant role in securing IoT networks. Designing an IDS that performs with maximum accuracy with minimum false alarms is a challenging task. Recently, the ensemble method considered one of the main developments in machine learning. It finds an accurate classifier by combining several classifiers. In this research, an ensemble classification model is proposed using an automatic Model Selection Method (MSM). The proposed MSM considered a vast range of classifiers with different configurations. Furthermore, The MSM used new integrated measures to evaluate and select models. The proposed models showed 0.99, 0.95, 1, and 0.99 F scores and 1, 0.98, 1, 1 ROC-AUC scores on NSL-KDD, UNSW-NB15, BoTNeTIoT, and BoTIoT dataset, respectively. The proposed models overcame all models in terms of efficiency and showed stable performance using a vast range of feature sets.
Keyword:
Ensemble learning
Network security
Cybersecurity
IDS
IoT
期刊
IF:
7.6
论文数:
1.9K
被引数:
6.9K
机构
引用论文
TSE-IDS: A Two-Stage Classifier Ensemble for Intelligent Anomaly-Based Intrusion Detection System.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
分享收藏Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things基于卷积和递归神经网络的物联网网络流量分类器IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容