Advertisement
Published in:
2018 | OriginalPaper | Chapter
Network Intrusion Detection System Using Ensemble of Binary Deep Learning Classifiers
Authors : Aniruddha Parvat, Souradeep Dev, Siddhesh Kadam, Jai Chavan
Published in: Smart Trends in Information Technology and Computer Communications
Publisher: Springer Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
An Intrusion Detection System (IDS) is a software or a device that monitors a network or system to detect malicious activities. A Network Intrusion Detection System (NIDS) helps to detect security breaches in a network. There are many challenges while developing an efficient and flexible NIDS. In this work, we propose an NIDS using an ensemble of multiple binary classifiers. Each binary classifier is deep learning model. Deep learning is a model of machine learning loosely based on the structure and functioning of biological neural networks. We test our system on a benchmark network intrusion dataset: NSL-KDD. We present the performance of the proposed system and compare it with previous works. We evaluate the system performance by checking the accuracy, precision, recall and f1-score values for both binary as well as five class classifier.