Intrusion Detection in Software Defined Network Using Deep Learning Approach
Bambang Susilo, Riri Fitri Sari
Abstract
The development of IoT technology and virtualization has made network management increasingly complex. Software-Defined Network has become a standard in virtualizing computer networks. With technology developing, more attacks on computer networks. Researchers have developed many ways to deal with attacks, one of the most developed methods is to use machine learning. To deal with attacks that occur needed new ways to deal with it. This research will discuss Software-Defined Network, attacks that can occur on SDN, propose flow traffic, and methods for classification of attacks using deep learning algorithms. This research uses the Python programming language, also utilized several packages such as pandas framework, NumPy, sci-kit learn, tensor flow, and seaborn. From the results of the study, it was found that the algorithm that had been developed could produce good accuracy with a different dataset.