A Signature based ransomware detection using convolutional neural network

Selvakumar, Rahul (2022) A Signature based ransomware detection using convolutional neural network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (708kB) | Preview

Abstract

In recent years, ransomware has been one of the most common types of cybersecurity threats to well-known businesses and organizations. Ransomware is a type of cryptovirology malware which threatens to block and publish the data on a computer system by encrypting it. Hence, there is a need to develop an effective method for detecting ransomware. Most of the proposed methods were used in identifying the ransomware during the execution stage. It's hard to say how long a programme needs to be examined to display its actual behaviour. In this paper, the ransomware is detected using Sha1 and MD5 signatures using a convolutional neural network. A convolutional neural network is used since it has the ability to extract and categorise the features using images and classify them with high accuracy. The proposed method achieves 97.04% accuracy. The results show that the technique is helpful and feasible for ransomware detection.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Ransomware; Deep learning; CNN; signature-based
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
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Tamara Malone
Date Deposited:	29 Dec 2022 15:40
Last Modified:	29 Dec 2022 15:40
URI:	https://norma.ncirl.ie/id/eprint/6055

Actions (login required)

View Item