Accelerated deep neural networks for enhanced Intrusion Detection System

Authors:
Publisher website
Google Scholar
Abstract
Network based communication is more vulnerable to outsider and insider attacks in recent days due to its wide spread applications in many fields. Intrusion Detection System (IDS) a software application or a hardware is a security mechanism that is able to monitor network traffic and find abnormal activities in the network. Machine learning techniques which have an important role in detecting the attacks were mostly used in the development of IDS. Due to huge increase in network traffic and different types of attacks, monitoring each and every packet in the network traffic is time consuming and computational intensive. Deep learning acts as a powerful tool by which thorough packet inspection and attack identification is possible. The parallel computing capabilities of the neural network make the Deep Neural Network (DNN) to effectively look through the network traffic with an accelerated performance. In this paper an accelerated DNN architecture is developed to identify the abnormalities in the network data. NSL-KDD dataset is used to compute the training time and to analyze the effectiveness of the detection mechanism.

This publication has 20 references indexed in Scilit: