Portal de Periódicos da CAPES

An Efficient Intrusion Detection Framework in Software-Defined Networking for Cyber Security Applications

2023; Springer Nature; Linguagem: Inglês

10.1007/978-981-19-8669-7_40

2190-3026

Meruva Sandhya Vani, Rajupudi Durga Devi, Deena Babu Mandru,

Advanced Malware Detection Techniques

The board of directors and mixed media mining strategies are excited about further research and development of the organization's traffic processes. Relying on a unified, programmable controller, security has recently become the most complex task in Software-Defined Networking (SDN). Next, observing the organization's traffic is essential to distinguish and discover outage anomalies in the SDN environment. Therefore, this paper provides an in-depth review and examination of the NSL-KDD dataset using five different clustering calculations: K-implies, further before, canopy, density-based computation, and expansion of exceptions (EM), contrasting these five calculations largely involving Waikato Environment Programming for Knowledge Analysis (WEKA). Additionally, this paper introduces an SDN-based outage identification framework that uses a deep learning (DL) model and the Knowledge Discovery in Databases (KDD) dataset. A deep learning technique is proposed to promote a successful SDN-based outage detection framework. The findings provide in-depth investigation and flawless intelligent investigation into the different types of attacks. In addition, the results show that the proposed deep learning strategy outperforms existing methods with regard to interrupt discovery performance. For the analyzed dataset, for example, the proposed technique achieves an identification accuracy of 94.21%.