INTRUDER DETECTION SYSTEM USING SUPPORT VECTOR MACHINE AND RANDOM FOREST
Author(s):
K.Shivaganesh, A.Jaya Sree, P.Rashmitha, V.Sanjay
Keywords:
Random forest, Support Vector Machine , KDD99 , Dynamic Learning Rate, Machine Learning , Intruder Detection System
Abstract
Intrusion Detection Systems (IDSs) are critical in ensuring the security of computer networks. The existing IDSs use various machine learning algorithms such as SVM and Random Forest to detect network intrusions. However, in real-world scenarios, the network traffic can be highly dynamic, and the intrusion patterns can change over time, making it challenging to detect new types of intrusions accurately. It is difficult to guarantee the success of any intrusion detection system due to the nonlinearity and number of features in the network traffic data stream. Several intrusion detection techniques with various degrees of accuracy have been developed to address this issue. As a result, choosing an efficient and reliable IDS method is an important subject in information security. For classification purposes in this work, two models were created, one based on Support Vector Machines (SVM), and the other on Random Forests (RF). According to the experimental data, both classifiers are efficient, with SVM having a marginally greater accuracy but taking longer to run. On the other hand, when given the right modelling parameters, RF generates similar accuracy far more quickly. By improving its accuracy, these classifiers can improve an IDS system. To choose the best intrusion detector for this dataset, we used the KDD'99 dataset. Our statistical research uncovered important problems that have a negative impact on the performance of the systems under examination and lead to inadequate assessments of techniques to anomaly identification. The KDD'99 dataset's enormous amount of redundant records is its main problem. With the help of this study's conclusions, SVM and RF can be used more effectively to improve performance and reduce the false-negative rate.
Article Details
Unique Paper ID: 159358

Publication Volume & Issue: Volume 9, Issue 11

Page(s): 1103 - 1107
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers