An Explorative Analysis Sampling Deep Learning and Non-Deep Learning Approach for Detecting and Mitigating DDOS Attacks in a Network

Anigbogu Kenechukwu Sylvanus, Anusiuba Overcomer Ifeanyi Alex, Orji Everistus Eze and Mbonu Chinedu Emmanuel
Additional contact information
Anigbogu Kenechukwu Sylvanus: Lecturer, Department of Computer Science, Nnamdi Azikiwe University Awka, Anambra State, Nigeria
Anusiuba Overcomer Ifeanyi Alex: Lecturer, Department of Computer Science, Nnamdi Azikiwe University Awka, Anambra State, Nigeria
Orji Everistus Eze: Lecturer, Department of Computer Science, Federal Polytechnic Ohodo Enugu State, Nigeria
Mbonu Chinedu Emmanuel: Researcher, Department of Computer Science, Nazarbayev University, Astana

International Journal of Research and Scientific Innovation, 2025, vol. 12, issue 4, 15-22

Abstract: The Internet is being used almost everywhere in the world now. As a result of that developing a system and network security that can detect anomalies, protect the internetwork, and predict future security threats is crucial because billions of devices are interconnected over the Internet. However, DDoS (Distributed Denial-of-Service) attacks are the most frequent and perilous threat to internet growth. New variants of DDoS attacks are highly advanced and complicated, and it is almost impossible to detect or mitigate by the existing intrusion detection systems and traditional methods. Fortunately, Machine Learning technologies enable the detection of DDoS traffic effectively. This paper reviewed the DDoS detection model based on machine learning techniques. We extracted the most used models with good deep and non-deep learning results from our literature review. We extracted the most used models with good deep and non-deep learning results from our literature review. We extracted the most used models with good deep and non-deep learning results from our literature review. APA_DDOS_Dataset which has proven results from the review was experimented with Multi-layer perceptron and Random forest, we specified the three correlated features with predicted classes that we used. It was discovered that both Multi-layer perceptron and Random forest were accurate and correctly predicted the type of network traffic with 80% and 78% accuracy with scaling. Future research can be extended by testing newer datasets on this model and then testing hybrid algorithms on the newer datasets.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.rsisinternational.org/journals/ijrsi/d ... 12-issue-4/15-22.pdf (application/pdf)
https://rsisinternational.org/journals/ijrsi/artic ... ttacks-in-a-network/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjc:journl:v:12:y:2025:i:4:p:15-22

Access Statistics for this article

International Journal of Research and Scientific Innovation is currently edited by Dr. Renu Malsaria

More articles in International Journal of Research and Scientific Innovation from International Journal of Research and Scientific Innovation (IJRSI)
Bibliographic data for series maintained by Dr. Renu Malsaria ().