IIARD International Institute of Academic Research and Development

RESEARCH JOURNAL OF PURE SCIENCE AND TECHNOLOGY (RJPST )

E-ISSN 2579-0536
P-ISSN 2695-2696
VOL. 7 NO. 1 2024
DOI: https://doi.org/10.56201/rjpst.v7.no1.2024.pg71.81

---

Security Framework for Detection of Denial of Service (DoS) Attack on Virtual Private Networks for Efficient Data Transmission

Anthony Edet, Uduakobong Udonna, Immaculata Attih, and Anietie Uwah

---

Abstract

This study delves into the problem of detecting Denial-of-Service (DoS) attacks on Virtual Private Network (VPN) servers and the detrimental impact of such attacks on network functionality. A DoS attack aims to overwhelm a server, rendering it incapable of providing services to legitimate users. A VPN, on the other hand, serves as a secure conduit for data transmission over the internet. DoS attacks on VPN servers disrupt the seamless flow of communication, causing potential data breaches and compromising the confidentiality, integrity, and availability of network resources. The adverse effects of DoS attacks on VPN servers are profound, ranging from service degradation to complete unavailability. Such disruptions can lead to a breakdown in communication channels, hindering user access to critical resources. Our approach to tackling this challenge involves a meticulous examination of key data features, including Traffic-Volume, Packet-Rate, Traffic-Diversity, Connection- Attempts, Connection-Duration, Protocol-Analysis, and Packet-Size-Distribution. Our dataset is sourced directly from a live server, our study employs the K-Nearest Neighbors (KNN) classification algorithm, to model and identify patterns associated with DoS attacks. Our findings reveal a high accuracy of 94% in detecting DoS attacks using the KNN model, showcasing the efficacy of our approach. The utilization of real-world data enhances the relevance and applicability of our research in practical cybersecurity scenarios

keywords:

DoS, VPN, Cybersecurity, KNN

---

References:

Maonan(2021). CENTIME: a direct comprehensive traffic features extraction for encrypted
traffic classification, in: Proceedings of the 2021 IEEE 6th International Conference
on Computer and
Communication Systems (ICCCS), IEEE.

Ramos V, Suárez OJ, Suárez S, Febles VM, Aguirre E, Zradzi?ski P, Rabassa LE, Celaya-
Echarri M,
Marina P, Karpowicz J, Falcone F, Hernández JA. (2022).
Electromagnetic assessment of UHF-RFID devices in healthcare environment.
Applied Sciences 12(20):10667 DOI 10.3390/app122010667.

Abugabah, A., Nizamuddin, N., & Abuqabbeh, A. (2020). A review of challenges and barriers
implementing RFID technology in the healthcare sector. Procedia Computer Science,
170(3), 1003– 1010. DOI: 10.1016/j.procs.2020.03.094.

DOWNLOAD PDF

---

Back