Detection and Mitigation of Security Anomalies in Software-Defined Networks Using Deep Learning-Based Traffic Classification

Security in Software-Defined Networking (SDN) has emerged as one of the primary challenges in modern information technology. Given the unique features of SDN, such as centralized control and programmable architecture, security breaches and anomalies can spread rapidly within these networks. This paper presents a novel approach for detecting and mitigating security anomalies in SDN by leveraging Deep Learning-based (DL) traffic classification. The proposed method employs advanced DL algorithms to identify abnormal behaviors and detect attacks with high accuracy. Simulation results demonstrate that the proposed model outperforms traditional methods in terms of efficiency and response time, making it a valuable tool for enhancing security in SDN environments. This paper contributes significantly to improving security techniques in Software-Defined Networking.

کلیدواژه ها:

Anomaly Detection ، Software-Defined Networks ، Deep Learning ، Machine Learning ، Traffic Classification ، Adaptive Thresholding