Intrusion Detection System Using Improved Convolution Neural Network

IEEE BASE PAPER ABSTRACT:

Network intrusion detection technology plays an important role in maintaining network security, the main work is to continuously detect the current network status, through the detection of abnormal behavior in the network state, timely warning to alert network managers. The timeliness and accuracy of the intrusion detection system (IDS) is critical to the availability and reliability of the current network. In response to the problems of high false alarm rate, low detection efficiency and limited functions commonly found in IDS, this paper first investigates the application of deep learning techniques to the field of network intrusion detection. With the ability of deep learning algorithms to automatically extract features from intrusion data and avoid the work of manually screening features, an intrusion detection method based on improved convolution neural networks is then proposed. The method is improved by introducing Inception module for optimal intrusion feature extraction based on the traditional convolution neural network. The inception module employs a parallel convolution structure with different filters, using convolution kernels of different sizes on each convolution line for multiple layer-by-layer operations and the various features of network intrusions in the data set are identified and clustered by means of stacking.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Decision Tree Classifier.

OUR PROPOSED ABSTRACT:

Unauthorized data or lawful networks that use legitimate user identities, back doors, or other network vulnerabilities are seriously threatened by intrusion. IDS systems are designed to find intrusions at different levels. The goal of the project is to utilize machine learning approaches based on decision trees for attack detection and classification to enhance the performance of the intrusion detection system. Intrusion Detection Systems (IDS) play a vital role in safeguarding computer networks from malicious attacks.

In this project, we propose an Intrusion Detection System that uses a Decision Tree Classifier to identify network attacks. The existing system used an Improved Convolution Neural Network for the same purpose. We have achieved a high level of accuracy for our proposed system, with both training and validation accuracy at 99%. The dataset used in our project is the KDD dataset, which is widely used for evaluating IDS.

We have classified the predicted results into two classes – Normal or Attack Class – using various attack types such as ipsweep, Neptune, nmap, satan, smurf, and other attacker. The proposed system’s implementation involves the preprocessing of the KDD dataset, which includes data cleaning, normalization, and feature selection. We have used a Decision Tree Classifier, which is a supervised machine learning algorithm, to classify the data into the two classes.

The algorithm makes decisions based on a tree-like structure, where each node represents a feature of the data, and the edges represent the decision rules. The proposed Intrusion Detection System using a Decision Tree Classifier is highly effective in identifying network attacks with a high level of accuracy. It can be deployed in various settings, including corporate networks, government agencies, and other organizations, to protect their data and systems from malicious attacks.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Xue Ying Li; Rui Tang; Wei Song, “Intrusion Detection System Using Improved Convolution Neural Network”, 2022 11th International Conference of Information and Communication Technology (ICTech)), IEEE Conference, 2022.

Python IEEE Projects

Intrusion Detection System Using Improved Convolution Neural Network