An intelligent zero trust secure framework for software defined networking.

Area of Science:

• Computer Science
• Network Security
• Cybersecurity

Background:

• Software-defined networking (SDN) shares security vulnerabilities with traditional networks.
• The SDN architecture's separation of control and data planes creates a vulnerable controller.
• Traditional perimeter defense models are insufficient against insider threats and vulnerabilities in SDN.

Purpose of the Study:

• To propose an intelligent zero-trust security framework (IZTSDN) for software-defined networking.
• To integrate deep learning and zero-trust architecture for enhanced network protection.
• To address the security challenges posed by SDN's unique architecture.

Main Methods:

• Developed an intelligent zero-trust security framework (IZTSDN) for SDN.
• Integrated a deep learning-based traffic anomaly detection mode (CALSeq2Seql).
• Utilized the Mininet simulation platform to create MiniIZTA for testing.

Main Results:

• The IZTSDN framework maintained approximately 80.5% throughput during network attacks.
• Achieved 99.56% accuracy in abnormal traffic detection on an SDN dataset.
• Demonstrated the reliability and availability of the proposed security framework.

Conclusions:

• IZTSDN effectively protects network resources and connections using zero-trust principles.
• The framework enables real-time analysis of user network behavior for continuous tracking.
• IZTSDN provides dynamic authorization, restricting malicious user access and enhancing overall network security.