Detecting Ddos Attack Using Deep Learning Techniques
Year: 2025
Type: article
Abstract: In the modern digital world, the robustness of cybersecurity frameworks is crucial for maintaining operational integrity and safeguarding organizational assets. Distributed Denial of Service (DDoS) attacks are a frequent and very destructive kind of cyber intrusion that must be recognized and avoided, this study presents a Deep Learning. Based Intrusion Detection System (IDS). Distributed Denial of Service (DDOS)flooding is one of the security flaws that seriously damages IoT systems. DDOS assaults cannot be prevented by conventional data filtering methods. To safeguard the security of IoT settings, a novel hybrid deep CNN model-based framework for identifying DDoS flooding assaults is put forth in this study. It is utilized to satisfy the security needs of IoT settings and to overcome the drawbacks of existing DDoS attack detection approaches. One dimensional (1D) CNN and two dimensional (2D) CNN are used with two and three convolutional layers, respectively, to build a Hybrid Deep CNN model.
Authors: Puvaneswaran -, Parthipan -, Nivetha -
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4408102665