Open Access

ARTICLE

Securing Cloud Computing from Flash Crowd Attack Using Ensemble Intrusion Detection System

Turke Althobaiti^1,2, Yousef Sanjalawe^3,*, Naeem Ramzan⁴

1 Department of Computer Science, Faculty of Science, Northern Border University (NBU), Arar, 73222, Saudi Arabia
2 Remote Sensing Unit, Northern Border University (NBU), Arar, 73222, Saudi Arabia
3 Deparment of Cybersecurity, American University of Madaba (AUM), Amman, 11821, Jordan
4 School of Engineering and Computing, University of West of Scotland, Paisley, PA1 2BE, UK

* Corresponding Author: Yousef Sanjalawe. Email:

(This article belongs to the Special Issue: Artificial Intelligence for Cyber Security)

Computer Systems Science and Engineering 2023, 47(1), 453-469. https://doi.org/10.32604/csse.2023.039207

Received 14 January 2023; Accepted 10 March 2023; Issue published 26 May 2023

Abstract

Flash Crowd attacks are a form of Distributed Denial of Service (DDoS) attack that is becoming increasingly difficult to detect due to its ability to imitate normal user behavior in Cloud Computing (CC). Botnets are often used by attackers to perform a wide range of DDoS attacks. With advancements in technology, bots are now able to simulate DDoS attacks as flash crowd events, making them difficult to detect. When it comes to application layer DDoS attacks, the Flash Crowd attack that occurs during a Flash Event is viewed as the most intricate issue. This is mainly because it can imitate typical user behavior, leading to a substantial influx of requests that can overwhelm the server by consuming either its network bandwidth or resources. Therefore, identifying these types of attacks on web servers has become crucial, particularly in the CC. In this article, an efficient intrusion detection method is proposed based on White Shark Optimizer and ensemble classifier (Convolutional Neural Network (CNN) and LighGBM). Experiments were conducted using a CICIDS 2017 dataset to evaluate the performance of the proposed method in real-life situations. The proposed IDS achieved superior results, with 95.84% accuracy, 96.15% precision, 95.54% recall, and 95.84% F1 measure. Flash crowd attacks are challenging to detect, but the proposed IDS has proven its effectiveness in identifying such attacks in CC and holds potential for future improvement.

---

Keywords

---