Open AccessIntrusion Detection System Using Deep Learning
Author(s) -
Irin Anna Solomon,
Aman Jatain,
Shalini Bhaskar Bajaj
Publication year - 2019
Publication title -
asian journal of computer science and technology
Language(s) - English
Resource type - Journals
eISSN - 2583-7907
pISSN - 2249-0701
DOI - 10.51983/ajcst-2019.8.2.2132
Subject(s) - intrusion detection system , computer science , artificial intelligence , anomaly based intrusion detection system , network packet , machine learning , scope (computer science) , artificial neural network , network security , deep learning , data mining , computer security , programming language
Intrusion detection system (IDS) plays a very critical part in identifying threats and monitoring malicious activities in networking system. The system administrators can use IDS to detect unauthorized access by intruders in different organizations. It has become an inevitable element to the security administration of every organization. IDSs can be generally categorized into two categories. The first group focuses on patterns/signatures of network packets/traffic and they identify network intrusions using rule-based matching. The second group uses machine learning (ML) based approaches such as supervised and/or semi-supervised learning and train IDS models on a collection of labeled and/or unlabeled network data. This method has obtained better detection compared to the previous method. This project paper’s scope involves implementing an intrusion detection system using deep learning technology for efficient detection of intrusion and intrusive activities that can cause disruption in the networking system. We use a Feed-forward Neural Network, a deep learning based technique, on KDD99 CUP – a commonly used dataset for network intrusion. In this paper the performance of the proposed system is compared with the existing previous work.