An efficient fi cient intrusion detection system for IoT security using CNN decision forest

被引:0
作者
Bella, Kamal [1 ]
Guezzaz, Azidine [1 ]
Benkirane, Said [1 ]
Azrour, Mourade [2 ]
Fouad, Yasser [3 ]
Benyeogor, Mbadiwe S. [4 ]
Innab, Nisreen [5 ]
机构
[1] Cadi Ayyad Univ, Technol Higher Sch Essaouira, Essaouira, Morocco
[2] Moulay Ismail Univ Meknes, Fac Sci & Tech, IDMS team, Errachidia, Morocco
[3] King Saud Univ, Coll Appl Engn, Dept Appl Mech Engn, Muzahimiyah Branch, Riyadh, Saudi Arabia
[4] Univ Munster, Inst Phys, Munster, Germany
[5] AlMaarefa Univ, Coll Appl Sci, Dept Comp Sci & Informat Syst, Riyadh, Saudi Arabia
关键词
IoT; Deep learning; Machine learning; Intrusion detection; Security; INTERNET; INTEGRATION; NETWORK; THINGS;
D O I
10.7717/peerj-cs.2290
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The adoption and integration of the Internet of Things (IoT) have become essential for the advancement of many industries, unlocking purposeful connections between objects. However, the surge in IoT adoption and integration has also made it a prime target for malicious attacks. Consequently, ensuring the security of IoT systems and ecosystems has emerged as a crucial research area. Notably, advancements in addressing these security threats include the implementation of intrusion detection systems (IDS), garnering considerable attention within the research community. In this study, and in aim to enhance network anomaly detection, we present a novel intrusion detection approach: the Deep Neural Decision Forest-based IDS (DNDFIDS). The DNDF-IDS incorporates an improved decision forest model coupled with neural networks to achieve heightened accuracy (ACC). Employing four distinct feature selection methods separately, namely principal component analysis (PCA), LASSO regression (LR), SelectKBest, and Random Forest Feature Importance (RFFI), our objective is to streamline training and prediction processes, enhance overall performance, and identify the most correlated features. Evaluation of our model on three diverse datasets (NSL-KDD, CICIDS2017, and UNSW-NB15) reveals impressive ACC values ranging from 94.09% to 98.84%, depending on the dataset and the feature selection method. Notably, our model achieves a remarkable prediction time of 0.1 ms per record. Comparative analyses with other recent random forest and Convolutional Neural Networks (CNN) based models indicate that our DNDF-IDS performs similarly or even outperforms them in certain instances, particularly when utilizing the top 10 features. One key advantage of our novel model lies in its ability to make accurate predictions with only a few features, showcasing an efficient fi cient utilization of computational resources.
引用
收藏
页数:34
相关论文
共 62 条
[21]   A Survey on IoT Security: Application Areas, Security Threats, and Solution Architectures [J].
Hassija, Vikas ;
Chamola, Vinay ;
Saxena, Vikas ;
Jain, Divyansh ;
Goyal, Pranav ;
Sikdar, Biplab .
IEEE ACCESS, 2019, 7 :82721-82743
[22]   Toward an intrusion detection model for IoT-based smart environments [J].
Hazman, Chaimae ;
Guezzaz, Azidine ;
Benkirane, Said ;
Azrour, Mourade .
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (22) :62159-62180
[23]   Toward an Online Network Intrusion Detection System Based on Ensemble Learning [J].
Hsu, Ying-Feng ;
He, ZhenYu ;
Tarutani, Yuya ;
Matsuoka, Morito .
2019 IEEE 12TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (IEEE CLOUD 2019), 2019, :174-178
[24]  
Hussein AH, 2019, INT J ADV COMPUT SC, V10, P77
[25]   Integration of Internet of Things and cloud computing: a systematic survey [J].
Jahantigh, Motahareh Nazari ;
Rahmani, Amir Masoud ;
Navimirour, Nima Jafari ;
Rezaee, Ali .
IET COMMUNICATIONS, 2020, 14 (02) :165-176
[26]  
Jing DS, 2019, INT CONF ASIC
[27]   Performance Comparison of Feature Selection Methods for Prediction in Medical Data [J].
Khalid, Nur Hidayah Mohd ;
Ismail, Amelia Ritahani ;
Aziz, Normaziah Abdul ;
Hussin, Amir Aatieff Amir .
SOFT COMPUTING IN DATA SCIENCE, SCDS 2023, 2023, 1771 :92-106
[28]   Deep Neural Decision Forests [J].
Kontschieder, Peter ;
Fiterau, Madalina ;
Criminisi, Antonio ;
Bulo, Samuel Rota .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1467-1475
[29]  
Lakshminarayana Deepthi Hassan, 2019, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), P1122, DOI 10.1109/ICMLA.2019.00187
[30]   Intrusion detection system: A comprehensive review [J].
Liao, Hung-Jen ;
Lin, Chun-Hung Richard ;
Lin, Ying-Chih ;
Tung, Kuang-Yuan .
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2013, 36 (01) :16-24