The week's pick
Reseach Article
DDOS Attacks Detection using Supervised Learning Methods - An Evaluation of different Machine Learning Algorithms
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 46 |
| Year of Publication: 2024 |
| Authors: G. Dayanandam, E. Srinivasa Reddy, D. Bujji Babu |
10.5120/ijca2024924099
|
G. Dayanandam, E. Srinivasa Reddy, D. Bujji Babu . DDOS Attacks Detection using Supervised Learning Methods - An Evaluation of different Machine Learning Algorithms. International Journal of Computer Applications. 186, 46 ( Nov 2024), 38-42. DOI=10.5120/ijca2024924099
Abstract
Nowadays, there is exponential growth rate in number of users connected to the internet. Due to this, it is possibility to generate huge network traffic. If there is increased in network traffic, then there is a chance of increasing in network attacks. Distributed Denial of Service (DDoS) attack is one of such network attacks which deny the legitimate access to the server. The server is flooded with huge number of requests beyond the server capacity. Therefore the detection of such attacks is very tedious task. Machine learning algorithms will help to detect such type of attacks effectively as compared to the statistical based detection methods. In this paper, the researcher calculated Nearby Zero Variance (NZV) variables and eliminated them from the original dataset. It will help the model to detect the attacks with more accuracy. Then the researcher applied PCV method to preprocess the data and traincontrol () function is used to fine tune the variables. The researcher applied four supervised machine learning algorithms i.e., SVM, Decision Tree with C4.5, Naïve Bayes and Neural Networks to evaluate the model. All models performed very well as compared to other existing machine learning algorithms with the average accuracy of above 99%. Out of four supervised machine learning algorithms, decision tree with C4.5 got the average accuracy of 0.997.
References
- https://nvlpubs.nist.gov/nistpubs/legacy/sp/nistspecialpublication800-145.pdf
- https://www.cloudflare.com/en-gb/learning/ddos/glossary/denial-of-service/
- https://www.radware.com/cyberpedia/ddos-attacks/
- www.analyticvidhya.com
- Bhosale K S, Nenova M & Iliev G, Intrusion detection in communication networks using different classifiers, in Tehno-Societal 2018 (Springer, Cham) 2020, 19-28
- Singhal S, Medeira P A, Singhal P & Khorajiya M, Detection of application layer DDoS attacks using big data technologies, J Discret Math Sci, 23(2) (2020) 563-571
- Roopak M, Tian G Y & Chambers J, Multi-objective-based feature selection for DDoS attack detection in IoT networks, IET Networks, 9(3) (2020) 120-127
- Swami R, Dave M & Ranga V, DDoS attacks and defense mechanisms using machine learning techniques for SDN, in Research Anthology on Combating Denial-of-Service Attacks (IGI Global) 2021, 248-264
- Dwivedi S, Vardhan M & Tripathi S, Defense against distributed DoS attack detection by using intelligent evolutionary algorithm, Int J Comput Appl, (2020), DOI: 10.1080/1206212X.2020.1720951.
- Hussain Y S, Network Intrusion Detection for Distributed Denial-of-Service (DDoS) Attacks using Machine Learning Classification Techniques (2020), http://hdl.hdandle.net/1828/11679.
- Doucette C, Broderick-Sander R, Toll B, Helsinger A, Soule N, Pal P, Zhou C & Paffenroth R, A robust principal component analysis approach to DoS-related network anomaly detection, Proc SPIE 11417, Cyber Sensing 2020, 114170B (27 April 2020); https://doi.org/10.1117/12.2562774.
- Rathore S, Park J H, Semi-supervised learning based distributed attack detection framework for IoT, Appl Soft Comput, 72 (2018) 79-89.
- Ravi N, Shalinie S M. Learning-driven detection and mitigation of DDoS attack in IoT via SDN-cloud architecture, IEEE Internet of Things Journal, 7(4) (2020), 3559-3570.
- Nesa N, Ghosh T & Banerjee I. Non-parametric sequence-based learning approach for outlier detection in IoT, Future Gener Comput Syst, 82 (2018) 412-21.
- http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
- cran.wustl.edu
Index Terms
Keywords