International Journal of Electrical and Computer Engineering (IJECE) Vol. 10, No. 5, October 2020, pp. 5514~5525 ISSN: 2088-8708, DOI: 10.11591/ijece.v10i5.pp5514-5525  5514 Journal homepage: http://ijece.iaescore.com/index.php/IJECE An intrusion detection system for packet and flow based networks using deep neural network approach Kaniz Farhana 1 , Maqsudur Rahman 2 , Md. Tofael Ahmed 3 1 Department of Computer Science and Engineering, Port City International University, Bangladesh 2 Faculty of Science and Engineering, Department of Computer Science and Engineering, Port City International University, Bangladesh 3 Faculty of Engineering, Department of Information and Communication Technology, Comilla University, Bangladesh Article Info ABSTRACT Article history: Received Jan 26, 2020 Revised Apr 13, 2020 Accepted Apr 26, 2020 Study on deep neural networks and big data is merging now by several aspects to enhance the capabilities of intrusion detection system (IDS). Many IDS models has been introduced to provide security over big data. This study focuses on the intrusion detection in computer networks using big datasets. The advent of big data has agitated the comprehensive assistance in cyber security by forwarding a brunch of affluent algorithms to classify and analysis patterns and making a better prediction more efficiently. In this study, to detect intrusion a detection model has been propounded applying deep neural networks. We applied the suggested model on the latest dataset available at online, formatted with packet based, flow based data and some additional metadata. The dataset is labeled and imbalanced with 79 attributes and some classes having much less training samples compared to other classes. The proposed model is build using Keras and Google Tensorflow deep learning environment. Experimental result shows that intrusions are detected with the accuracy over 99% for both binary and multiclass classification with selected best features. Receiver operating characteristics (ROC) and precision-recall curve average score is also 1. The outcome implies that Deep Neural Networks offers a novel research model with great accuracy for intrusion detection model, better than some models presented in the literature. Keywords: Big data Deep neural networks Intrusion detection system (IDS) Keras Tensorflow Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Kaniz Farhana, Department of Computer Science and Engineering, Port City International University (PCIU), Chittagong, Bangladesh. Phone +8801857979984 Email: kanizbips@gmail.com 1. INTRODUCTION Information and communication technology (ICT) now poses a great challenge for network engineers because of its growth over the years. Along with the advancement in the technologies the amount of threat is also increasing and handling big datasets has also become an important factor when it comes to security. For years, research on network security has been followed by a great focus and interest by the researchers. Threats can bring huge damage to systems and organizations. The challenge is to detect those intrusions over the big data and network. To detect these attacks, the network intrusion detection system (IDS) has shown great significance on the platforms that need constant security monitoring and we can say that intrusion detection is mandatory for protecting any system from malicious activities and keep the system secure to perform precisely. An intrusion detection system is a type of system that scans through the traffic of networks and looks for potential suspicious activities, analyzes those activities, alerts the system