Edge-HetIoT defense against DDoS attack using learning techniques

Shalaka S. Mahadik; Pranav M. Pawar; Raja Muthalagu

doi:10.1016/j.cose.2023.103347

Edge-HetIoT defense against DDoS attack using learning techniques

Shalaka S. Mahadik, Pranav M. Pawar, Raja Muthalagu

Birla Institute of Technology and Science Pilani

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

The heterogeneous nature of the internet-of-thing (IoT) is gaining popularity and, simultaneously, faces rising security issues. The distributed denial of service (DDoS) attack is the most significant security threat addressed in the research. The research proposes edge-heterogeneous IoT (HetIoT) centric defense IDS that aids the HetIoT infrastructure in detecting and blocking victim traffic near the network edge. The Edge-HetIoT defense IDS helps to address significant issues such as performance and security due to proximity to the local network. The research focuses on six learning techniques, including five machine learning (ML) classifiers, namely, ID3, NB, RF, LR, and AdaBoost, and the proposed deep learning (DL)-based hybrid model (i.e., CNN+LSTM). These learning techniques are trained and tested using the real-time benchmark-dataset CICDDoS2019 and consider binary and multiclass (14 classes) classification. The performance is analyzed and evaluated against six classifiers to determine which classification model performs best in detecting and classifying various DDoS attacks. The proposed DL-based hybrid model outperforms when compared against ID3, NB, RF, LR, and AdaBoost. The proposed DL-based hybrid model successfully detects and classifies MSSQL, NetBIOS, TFTP, NTP, Syn, and Portmap attacks with 100% precision, recall, and f1-score. The overall weighted average precision, recall, and f1-score for the proposed DL-based hybrid model are 92%, 89%, and 90%, respectively.

Original language	English
Article number	103347
Journal	Computers and Security
Volume	132
DOIs	https://doi.org/10.1016/j.cose.2023.103347
State	Published - Sep 2023
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2023 Elsevier Ltd

Funding

Dr. Pranav M. Pawar graduated in Computer Engineering from Dr. Babasaheb Ambedkar Technological University, Maharashtra, India, in 2005, received a Master in Computer Engineering from Pune University, in 2007, and received Ph.D. in Wireless Communication from Aalborg University, Denmark in 2016, his Ph.D. thesis received a nomination for Best Thesis Award from Aalborg University, Denmark. Currently, he is working as an Assistant Professor in the Dept of Computer Science, Birla Institute of Technology and Science, Dubai, before BITS he was a postdoctoral fellow at Bar-Ilan University, Israel from March 2019 to October 2020 in the area of Wireless Communication and Deep Leaning. He is the recipient of an outstanding postdoctoral fellowship from the Israel Planning and Budgeting Committee. He worked as an Associate Professor at MIT ADT University, Pune from 2018-to 2019 and also as an Associate Professor in the Department of Information Technology, STES’s Smt. Kashibai Navale College of Engineering, Pune from 2008 to 2018. From 2006 to 2007, was working as System Executive in POS-IPC, Pune, India. He received Recognition from Infosys Technologies Ltd. for his contribution to the Campus Connect Program and also received different funding for research and attending conferences at the international level. He published more than 40 papers at the national and international levels. He is IBM DB2 and IBM RAD certified professional and completed NPTEL certification in different subjects. His research interests are Energy efficient MAC for WSN, QoS in WSN, wireless security, green technology, computer architecture, database management system, and bioinformatics.

Funders	Funder number
Planning and Budgeting Committee of the Council for Higher Education of Israel

Keywords

CNN and LSTM
DDoS attack
Deep learning (DL)
Edge computing
Heterogeneous Internet-of-Things
Hybrid
Machine learning (ML)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.cose.2023.103347

Cite this

@article{da8df6f5784e4f9383b50e0ee4c6f370,

title = "Edge-HetIoT defense against DDoS attack using learning techniques",

abstract = "The heterogeneous nature of the internet-of-thing (IoT) is gaining popularity and, simultaneously, faces rising security issues. The distributed denial of service (DDoS) attack is the most significant security threat addressed in the research. The research proposes edge-heterogeneous IoT (HetIoT) centric defense IDS that aids the HetIoT infrastructure in detecting and blocking victim traffic near the network edge. The Edge-HetIoT defense IDS helps to address significant issues such as performance and security due to proximity to the local network. The research focuses on six learning techniques, including five machine learning (ML) classifiers, namely, ID3, NB, RF, LR, and AdaBoost, and the proposed deep learning (DL)-based hybrid model (i.e., CNN+LSTM). These learning techniques are trained and tested using the real-time benchmark-dataset CICDDoS2019 and consider binary and multiclass (14 classes) classification. The performance is analyzed and evaluated against six classifiers to determine which classification model performs best in detecting and classifying various DDoS attacks. The proposed DL-based hybrid model outperforms when compared against ID3, NB, RF, LR, and AdaBoost. The proposed DL-based hybrid model successfully detects and classifies MSSQL, NetBIOS, TFTP, NTP, Syn, and Portmap attacks with 100% precision, recall, and f1-score. The overall weighted average precision, recall, and f1-score for the proposed DL-based hybrid model are 92%, 89%, and 90%, respectively.",

keywords = "CNN and LSTM, DDoS attack, Deep learning (DL), Edge computing, Heterogeneous Internet-of-Things, Hybrid, Machine learning (ML)",

author = "Mahadik, {Shalaka S.} and Pawar, {Pranav M.} and Raja Muthalagu",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier Ltd",

year = "2023",

month = sep,

doi = "10.1016/j.cose.2023.103347",

language = "אנגלית",

volume = "132",

journal = "Computers and Security",

issn = "0167-4048",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Edge-HetIoT defense against DDoS attack using learning techniques

AU - Mahadik, Shalaka S.

AU - Pawar, Pranav M.

AU - Muthalagu, Raja

PY - 2023/9

Y1 - 2023/9

N2 - The heterogeneous nature of the internet-of-thing (IoT) is gaining popularity and, simultaneously, faces rising security issues. The distributed denial of service (DDoS) attack is the most significant security threat addressed in the research. The research proposes edge-heterogeneous IoT (HetIoT) centric defense IDS that aids the HetIoT infrastructure in detecting and blocking victim traffic near the network edge. The Edge-HetIoT defense IDS helps to address significant issues such as performance and security due to proximity to the local network. The research focuses on six learning techniques, including five machine learning (ML) classifiers, namely, ID3, NB, RF, LR, and AdaBoost, and the proposed deep learning (DL)-based hybrid model (i.e., CNN+LSTM). These learning techniques are trained and tested using the real-time benchmark-dataset CICDDoS2019 and consider binary and multiclass (14 classes) classification. The performance is analyzed and evaluated against six classifiers to determine which classification model performs best in detecting and classifying various DDoS attacks. The proposed DL-based hybrid model outperforms when compared against ID3, NB, RF, LR, and AdaBoost. The proposed DL-based hybrid model successfully detects and classifies MSSQL, NetBIOS, TFTP, NTP, Syn, and Portmap attacks with 100% precision, recall, and f1-score. The overall weighted average precision, recall, and f1-score for the proposed DL-based hybrid model are 92%, 89%, and 90%, respectively.

AB - The heterogeneous nature of the internet-of-thing (IoT) is gaining popularity and, simultaneously, faces rising security issues. The distributed denial of service (DDoS) attack is the most significant security threat addressed in the research. The research proposes edge-heterogeneous IoT (HetIoT) centric defense IDS that aids the HetIoT infrastructure in detecting and blocking victim traffic near the network edge. The Edge-HetIoT defense IDS helps to address significant issues such as performance and security due to proximity to the local network. The research focuses on six learning techniques, including five machine learning (ML) classifiers, namely, ID3, NB, RF, LR, and AdaBoost, and the proposed deep learning (DL)-based hybrid model (i.e., CNN+LSTM). These learning techniques are trained and tested using the real-time benchmark-dataset CICDDoS2019 and consider binary and multiclass (14 classes) classification. The performance is analyzed and evaluated against six classifiers to determine which classification model performs best in detecting and classifying various DDoS attacks. The proposed DL-based hybrid model outperforms when compared against ID3, NB, RF, LR, and AdaBoost. The proposed DL-based hybrid model successfully detects and classifies MSSQL, NetBIOS, TFTP, NTP, Syn, and Portmap attacks with 100% precision, recall, and f1-score. The overall weighted average precision, recall, and f1-score for the proposed DL-based hybrid model are 92%, 89%, and 90%, respectively.

KW - CNN and LSTM

KW - DDoS attack

KW - Deep learning (DL)

KW - Edge computing

KW - Heterogeneous Internet-of-Things

KW - Hybrid

KW - Machine learning (ML)

UR - http://www.scopus.com/inward/record.url?scp=85163167118&partnerID=8YFLogxK

U2 - 10.1016/j.cose.2023.103347

DO - 10.1016/j.cose.2023.103347

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85163167118

SN - 0167-4048

VL - 132

JO - Computers and Security

JF - Computers and Security

M1 - 103347

ER -

Edge-HetIoT defense against DDoS attack using learning techniques

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this