NETWORK INTRUSION DETECTION SYSTEM USING DEEP LEARNING









Abstract

The advent of abundant communication paradigm and increased number of networked digital devices in recent years is a growing concern in cyber security which tries to preserve either the information or the communication technology of the system. Intruders uncover new types of attack everyday, in-order to prevent these attacks, they must be recognised correctly by the used intrusion detection systems (IDS's), and then proper responses should be given. To aid monitoring the network traffic in case of attacks, this system is now known as Network Intrusion Detection System (NIDS). In NIDS, the detection system examines the incoming and outgoing network traffic from all hosts in real time. On a certain basis, it can detect and identify the attack, then take the suitable security measures to stop or block it, which significantly reduces the risk of damage to the network. The challenge with the existing literature is its reliance on datasets with shortcomings and issues to train ANIDS models. To Achieve this, an algorithm of Convolutional Neural Network(CNN) for classifying the firmware assault in network traffic. A Deep Learning algorithm, Convolutional Neural Network (CNN) that takes in an input image and assigns importance (learnable weights and biases) to various aspects/objects in the image & aids in differentiating one from another. We use CNN as a model for finding accuracy in the CSE-CICIDS2018 dataset.


Modules


Algorithms


Software And Hardware