Call For Paper Volume: V, Issue: 08 | AUGUST 2026 | International Journal of Advanced Trends in Engineering and Management (IJATEM)
Volume V | Issue 1 | 2026 | Paper ID: IJATEM-V05I01P4

An Efficient Intrusion Detection Framework for Software-Defined Networks Using Chaotic Panda Optimization and Multi-Scale Transformer Attention Network

, P. Kavitha

Software-Defined Networks (SDN) have emerged as a flexible networking paradigm by separating the mechanism plane from the data plane, allowing centralized network managing as well as dynamic traffic control. In this paper an Efficient Intrusion Detection (ID) Framework based on Chaotic Panda Optimization (CPO) and a Multi-Scale Transformer Attention Network (MSTAN) Intrusion Detection (ID) for SDN environments. A network traffic data are collected and pre-processed through data cleaning and missing value handling to improve data quality. Data visualization is then performed to analyse traffic patterns and identify abnormal behaviours, followed by feature selection to retain the most informative attributes. The proposed MSTAN captures both local as well as global dependences in network traffic through multi-scale attention mechanisms for accurate ID. Further to improve MSTAN parameter the CPO algorithm is used enhancing convergence speed and detection performance. Experimental results is demonstrated in Python software using SDN Intrusion Detection dataset the proposed structure attains an accuracy of 99.3%, outperforming existing ID approaches. The proposed framework provides an intelligent, reliable, and computationally efficient solution for real-time ID in SDN.

Software-Defined Networks, Intrusion Detection, Chaotic Panda Optimization, Multi-Scale Transformer Attention Network

  • [1] Sasi Rekha Sankar; B. Jothi., Year: 2026, “EGOA-DL-IDS: explainable intrusion detection in SDN-based industrial cyber physical system with optimized deep learning techniques,” Cluster Computing, Vol: 29, No: 4, pp. 242.

  • [2] USMAN Ahmed; Muhammad Tariq Sadiq, Year: 2026, “Enhancing SDN Intrusion Detection via Multi-Hybrid Deep Learning Fusion and Explainable AI,” Mathematics, Vol: 14, No: 9, pp. 1498.

  • [3] Sheikh Abdul Wahab; Saira Sultana; Noshina Tariq; Maleeha Mujahid; Javed Ali Khan; Alexios Mylonas, Year: 2025, “A multi-class intrusion detection system for DDoS attacks in IoT networks using deep learning and transformers,” Sensors 25, No: 15,pp. 4845.

  • [4] K. Sivakumar; Kakoli Banerjee; R. Vibin; B. Saravanan; Satyajee Srivastava; R. Anand; V. Bhoopathy, Year: 2024, “AI-driven green network management for future Internet and software-defined networking (SDN),”.

  • [5] Ayşe Okutan Kara; Aytuğ Boyacı, Year: 2026, “Transformer–DDQN-Based Explainable and Active Intrusion Detection Architecture for Network Traffic Analysis,”Applied Sciences, Vol: 16, No: 12, pp. 5912.

  • [6] Laraib Sana; Muhammad Mohsin Nazir; Jing Yang; Lal Hussain; Yen-Lin Chen; Chin Soon Ku; Mohammed Alatiyyah, Sulaiman Abdullah Alateyah, and Lip Yee Por, Year: 2024, “Securing the IoT cyber environment: Enhancing intrusion anomaly detection with vision transformers,” IEEE Access, Vol: 12, pp. 82443-82468.

  • [7] Zhenyue Long; Huiru Yan; Guiquan Shen; Xiaolu Zhang; Haoyang He; Long Cheng, Year: 2024, “A Transformer-based network intrusion detection approach for cloud security,” Journal of Cloud Computing, Vol: 13, No: 1, pp. 5.

  • [8] Mohammed N Swileh; Shengli Zhang, Year: 2025, “Unseen attack detection in software-defined networking using a BERT-based large language model,”AI, Vol: 6, No: 7, pp. 154.

  • [9] Sirajudeen Ameer John; Senthilnathan Palaniappan P; Gopichand G; Ganesan G, Year: 2026, “Advanced IoT intrusion detection using hybrid attention-based deep learning with DenseNet-ViT and AlexNet-BERT,” Journal of Cloud Computing.

  • [10] Jamal Alotaibi, Year: 2025, “A hybrid software-defined networking approach for enhancing IoT cybersecurity with deep learning and blockchain in smart cities,” Peer-to-Peer networking and Applications, Vol: 18, No: 3, pp. 123.

  • [11] Majid H Alsulami, Year: 2024, “Residual dense optimization-based multi-attention transformer to detect network intrusion against cyber-attacks,” Applied Sciences, Vol: 14, No: 17, pp. 7763.

  • [12] G. B Veeresh; Vanita Jaitly; V. Lokeswara Reddy, Year: 2025, “Swish-Optimized trident fusion network for precise attack classification in software-defined networks,” Knowledge-Based Systems, pp. 114860.