Year: 2024
Type: article
Abstract: Botnet attacks pose a significant threat to the security and stability of software-defined networks (SDNs). Traditional methods for detecting and mitigating botnet attacks often rely on signature-based detection or rule-based systems, which may struggle to adapt to evolving attack techniques. In this paper, we propose a novel approach for detecting and mitigating botnet attacks in SDNs using deep learning techniques. Our method leverages the capabilities of deep learning models, specifically convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to automatically learn and extract features from network traffic data. By training these models on labeled datasets of normal and botnet traffic, we can effectively distinguish between benign and malicious activity in real-time. Additionally, we integrate our deep learning-based detection system with SDN controllers to enable proactive mitigation of botnet attacks. Experimental results demonstrate the effectiveness of our approach in accurately detecting and mitigating botnet attacks while minimizing false positives. Overall, our proposed method provides a promising solution for enhancing the security of SDNs against botnet threats.
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4403851057