Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188655,
        author = {Mr. Janak Maru and Dr. Ashish Kothari},
        title = {Deep Learning-Driven Framework for DDoS Attack Prevention in Software Defined Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {2537-2542},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188655},
        abstract = {Software-Defined Networking (SDN) introduces centralized control and dynamic network programmability, but its logically centralized controller is a prime target for Distributed Denial of Service (DDoS) assaults. Traditional intrusion detection systems (IDS) frequently fail to deliver fast and accurate detection of dynamically changing attack patterns in SDN. To address these problems, this study provides an intelligent DDoS assault mitigation architecture that combines Deep Learning (DL) with a Random Forest-based Intrusion Detection System (IDS) to enable effective and scalable threat management in SDN environments. The proposed model employs deep learning approaches to extract high-level, discriminative traffic data, while the Random Forest classifier provides strong multi-class classification for attack detection. When compared to traditional machine learning methods, this combination greatly improves detection accuracy, minimizes false positives, and speeds up reaction time. The SDN controller automatically deploys mitigation techniques based on detection alarms, allowing for real-time traffic control, adaptive flow rule implementation, and network resource protection. Experimental results show that the hybrid DL-Random Forest IDS outperforms other methods in identifying various DDoS attack types, ensuring dependable and long-term SDN functioning. The findings demonstrate the potential of hybrid intelligence-driven security mechanisms in protecting next-generation programmable networks from large-scale cyber assaults.},
        keywords = {Software-Defined Networking (SDN), DDoS Detection, Intrusion Detection System (IDS), Deep Learning, Random Forest, Traffic Classification, Network Security, Controller Protection, Real-Time Mitigation, DDoS Attack Analysis},
        month = {December},
        }