Open Access
Pragati Pejlekar
Shlok Gautam Gamare
Vedant Thaksen Gavhane
Vishal Namdeo Kamble
- Assistant Professor, Saraswati, College of Engineering, Khargha, , India
- student, Saraswati, College of Engineering, Khargha, , India
- student, Saraswati, College of Engineering, Khargha, , India
- student, Saraswati, College of Engineering, Khargha, , India
Abstract
Intrusion detection system is a software program developed to use on computer systems so that it can identify intrusion attack with help of different techniques like the machine learning algorithms. The variety of assaults over the internet has multiplied through the years because of the development and smooth availability of computing technologies. Attackers develop new attack types, so in order to save you from those assaults, intrusion detection systems must first be successfully identified (IDS). An intrusion Detection System (IDS) is used to maintain security of network. The supervised machine learning system is designed to scan network traffic whether it is malicious or benign. To have best intrusion attack detection success rate, a combination machine learning algorithm and feature selection method has been used. In this study, we have used the machine learning algorithm Artificial Neural Network (ANN) with feature selection from network traffic. We downloaded the training dataset from NSL-KDD to classify network packets using machine learning methods like ANN algorithm. Machine learning algorithms are better to detect intrusion and can protect systems efficiently. We have trained machine learning algorithm on dataset from NSL-KDD to detect type of intrusion attack. We have used Wireshark to capture network packets and filter them, so the ANN machine learning algorithm can use these filtered packets to detect what type of attack was done on computer system.
Keywords: Intrusion detection, machine learning, supervised learning, NSL-KDD dataset
[This article belongs to Journal Of Network security(jons)]
Browse Figures
References
1. Biswas SK. Intrusion detection using machine learning: A comparison study. Int J Pure Appl Math. 2018 Feb; 118(19): 101–14. 2. Chowdhury MN, Ferens K, Ferens M. Network intrusion detection using machine learning. In Proceedings of the International Conference on Security and Management (SAM). 2016; 30–35. The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). 3. Jamadar RA. Network intrusion detection system using machine learning. Indian J Sci Technol. 2018 Dec; 7(48): 1–6. 4. Repalle SA, Kolluru VR. Intrusion detection system using ai and machine learning algorithm. Int Res J Eng Technol (IRJET). 2017 Dec; 4(12): 1709–15. 5. Samriddhi V, Nithyanandam P. Detailed analysis of intrusion detection using machine learning algorithms. Int J Recent Technol Eng (IJRTE). 2020; 9(1): 1894–1899. 6. Kim J, Kim J, Kim H, Shim M, Choi E. CNN-based network intrusion detection against denial-of-service attacks. Electronics. 2020 Jun; 9(6): 916. 7. Chandre PR, Mahalle PN, Shinde GR. Intrusion Prevention Framework for WSN using Deep CNN. Turkish Journal of Computer and Mathematics Education (TURCOMAT). 2021 May 22; 12(6): 3567–72. 8. Halimaa A, Sundarakantham K. Machine learning based intrusion detection system. In 2019 IEEE 3rd International conference on trends in electronics and informatics (ICOEI). 2019 Apr 23; 916–920. 9. Kumar MR, Malathi K. An Innovative Method in Improving the accuracy in Intrusion detection by comparing Random Forest over Support Vector Machine. In 2022 IEEE International Conference on Business Analytics for Technology and Security (ICBATS). 2022 Feb 16; 1–6. 10. Kejriwal S, Patadia D, Dagli S, Tawde P. Machine Learning Based Intrusion Detection. In 2022 IEEE 4th International Conference on Advances in Electronics, Computers and Communications (ICAECC). 2022 Jan 10; 1–5.
Journal Of Network security
| Volume | 10 |
| Issue | 1 |
| Received | May 12, 2022 |
| Accepted | May 23, 2022 |
| Published | January 30, 2023 |