METHOD FOR DETECTING NETWORK INTRUSIONS

Abstract

ABSTRACT A method (100) for detecting network intrusions, the method (100) comprising the steps of capturing a network traffic data from a monitored network, pre-processing the captured data by scaling numerical features and encoding categorical features to prepare for analysis, selecting relevant features from the pre-processed data based on correlation of the numerical features and the categorical features with known intrusion patterns, applying a machine learning model to classify the network traffic data as normal or anomalous and generating an alert if the network traffic is classified as anomalous. <>

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to a field of network intrusions and in particular relates to a method for detecting network intrusions.
BACKGROUND
[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] In modern networked environments, the increase in connectivity has led to a significant rise in cyber threats. Networks are frequently targeted by intruders seeking unauthorized access to sensitive data, often exploiting network vulnerabilities to perform malicious activities. Effective network sec , Claims:1. A method (100) for detecting network intrusions, the method (100) comprising the steps of:
capturing a network traffic data from a monitored network;
pre-processing the captured data by scaling numerical features and encoding categorical features to prepare for analysis;
selecting relevant features from the pre-processed data based on correlation of the numerical features and the categorical features with known intrusion patterns;
applying a machine learning model to classify the network traffic data as normal or anomalous; and
generating an alert if the network traffic is classified as anomalous.

2. The method (100) as claimed in claim 1, the machine learning model comprises a Decision Tree Classifier, Naive Bayes, and K-Nearest Neighbours classifiers.

3. The method (100) as claimed in claim 2, further comprising reducing false positives and improving detection accuracy by selecting the relevant features and applying the machine learning model.

Documents