Thota, Srilakshmi (2024) Predictive Modelling for Early Detection and Prevention of Ransomware, and Malware Using Machine Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (132kB) | Preview |
Abstract
In the digital arena, the growing frequency of ransomware and malware attacks makes efficient detection and mitigating techniques ever more crucial. This study focuses on machine learning techniques for ransomware and virus detection. We want to develop detection models that, with the help of advanced algorithms and preprocessing methods, can correctly identify dangerous software. The Random Forest model outperformed all the other models with high accuracy and F1-score. Other methods like K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) also performed very well the accuracy of KNN was close to one while, using methods such as SMOTE and ADASYN, SVM also exhibited high level of accuracy. Other techniques, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) provided much higher accuracy, 99. As for instance, SMOTE achieved an average accuracy of 98% confirming its capacity for handling data despite having been synthesized for sequential pattern data. Logistic Regression was the most accurate with a percentage of 93.83%. These findings demonstrate the effectiveness of sophisticated machine learning models in the detection of malware and ransomware. The solution that we have made is a response system. When this system is deployed into any kind of environment it will help in monitoring the system. In that the API can be integrated to any enterprise server. This response system monitors in such a way that the solution can generate the log files of the intrusions or suspicious activity in the form of malware or ransomware.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Salahuddin, Jawad UNSPECIFIED |
Uncontrolled Keywords: | Machine learning; Ransomware and malware; Logistic; SVM; Cybersecurity; Modeling |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Cyber Security |
Depositing User: | Ciara O'Brien |
Date Deposited: | 31 Jul 2025 11:54 |
Last Modified: | 31 Jul 2025 11:54 |
URI: | https://norma.ncirl.ie/id/eprint/8380 |
Actions (login required)
![]() |
View Item |