Classification and detection of ransomware using machine learning algorithms

M.Amin, Rabbiatul Addawiyah (2024) Classification and detection of ransomware using machine learning algorithms. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

Text (Full Text) Classification and detection of ransomware using machine learning algorithms.pdf - Submitted Version Download (25MB)

Abstract

The evolving landscape of cyber threats necessitates the development of robust and adaptable security solutions. Malicious attacks, malware, and particularly ransomware families pose significant challenges, with the potential to cause catastrophic damage to computer systems, data centers, and web and mobile applications across various sectors. Traditional anti-ransomware systems often struggle to keep pace with the sophistication of newly created attacks. Consequently, there is a growing need for state-of-the-art techniques, including traditional machine learning algorithms and cutting-edge neural network architectures, to be leveraged in the development of innovative ransomware detection and prevention solutions. This paper proposes a feature selection-based framework that utilizes various machine learning algorithms, including neural network architectures, for ransomware classification. The framework aims to classify the severity level of ransomware samples to aid in detection and prevention efforts. We evaluate the performance of several machine learning algorithms, including Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Neural Network (NN)-based classifiers, using a selected set of ransomware features. All experiments are conducted on a single ransomware dataset to assess the efficacy of the proposed framework. The results of our experiments suggest that Random Forest classifiers achieve superior performance compared to other methods in terms of accuracy, F1-score, and precision.

Actions (login required)

View Item