Title: Fortifying cyber defence: unveiling the power of convolutional neural networks and cutting-edge data preprocessing methods for DDoS attack detection in the digital frontier

Authors: Chris Harry Kandikattu; Sam Sangeeth Panguluri; Sandeep Kumar; Suneetha Bulla; Abdul Raheem Shaik

Addresses: Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundations, Vijayawada, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundations, Vijayawada, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundations, Vijayawada, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundations, Vijayawada, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundations, Vijayawada, India

Abstract: With a global increase in the frequency of cyberattacks in the internet space, the digital sphere faces a significant upheaval in danger to an individual's online presence and corporate entities. The work put forward in this paper takes advantage of deep learning techniques to improve security against DDoS attacks. The research paper provides a holistic approach to detecting DDoS attacks using convolutional neural networks (CNNs) combined with advanced data preprocessing methods. The proposed work in this research paper has been evaluated using two widely known and publicly available datasets, namely NSL-KDD and CSE-CIC-IDS208. The proposed work demonstrates that the proposed methodology consistently outperforms both datasets, achieving impressive accuracy scores of 97.46% and 98.53%. These findings underscore the promising potential of the proposed approach in enhancing the accuracy and effectiveness of intrusion detection systems.

Keywords: distributed denial of service; DDoS; cloud attacks; cloud environment; cloud security.

DOI: 10.1504/IJESMS.2025.146205

International Journal of Engineering Systems Modelling and Simulation, 2025 Vol.16 No.3, pp.126 - 134

Received: 18 Dec 2023
Accepted: 15 Feb 2024
Published online: 12 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article