Improving security using SVM-based anomaly detection: issues and challenges
- PDF / 3,830,559 Bytes
- 29 Pages / 595.276 x 790.866 pts Page_size
- 24 Downloads / 272 Views
(0123456789().,-volV)(0123456789().,-volV)
METHODOLOGIES AND APPLICATION
Improving security using SVM-based anomaly detection: issues and challenges Mehdi Hosseinzadeh1,2 • Amir Masoud Rahmani3 • Bay Vo4 • Moazam Bidaki5 • Mohammad Masdari6 Mehran Zangakani7
•
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Security is one of the main requirements of the current computer systems, and recently it gains much importance as the number and severity of malicious attacks increase dramatically. Anomaly detection is one of the main branches of the intrusion detection systems which enables to recognize the newer variants of the security attacks. This paper focuses on the anomaly detection schemes (ADS), which have applied support vector machine (SVM) for detecting intrusions and security attacks. For this purpose, it first presents the required concepts about the SVM classifier and intrusion detection systems. It then classifies the ADS approaches and discusses the various machine learning and artificial intelligence techniques that have been applied in combination with the SVM classifier to detect anomalies. Besides, it specifies the primary capabilities, possible limitations, or advantages of the ADS approaches. Furthermore, a comparison of the studied ADS schemes is provided to illuminate their various technical details. Keywords SVM Multiclass SVM Anomaly intrusion detection Feature selection Security PCA
Communicated by V. Loia. 4
Faculty of Information Technology, Ho Chi Minh City University of Technology (HUTECH), Ho Chi Minh City, Vietnam
Mehdi Hosseinzadeh [email protected]
5
Computer Engineering Department, Urmia Branch, Islamic Azad University, Urmia, Iran
Amir Masoud Rahmani [email protected]
6
Department of Computer Engineering, Neyshabur Branch, Islamic Azad University, Neyshabur, Iran
Moazam Bidaki [email protected]
7
Afagh Higher Education Institute, Urmia, Iran
& Bay Vo [email protected]
Mohammad Masdari [email protected] Mehran Zangakani [email protected] 1
Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam
2
Health Management and Economics Research Center, Iran University of Medical Sciences, Tehran, Iran
3
Department of Computer Science, Khazar University, Baku, Azerbaijan
123
M. Hosseinzadeh et al.
1 Introduction
classified into the following categories (Ahmed et al. 2016):
Almost all TCP/IP layers are vulnerable to some kinds of malicious behaviors and security attacks, which may be conducted by internal or external attackers (Yan et al. 2015; Singh et al. 2016). However, network hacking and attacking methods are evolving every day to keep security pressure on the computing technologies and networks such as the Internet of Things (IoT) (Qi et al. 2017; Alaba et al. 2017), wireless body area networks (WBANs) (Yessad et al. 2018; Masdari et al. 2017), eHealthcare systems (Yaseen et al. 2018; Masdari and Ahmadzadeh 2017), and cloud computing (Ghomi et al. 2017; Masdari and Zang
Data Loading...
