Skip to main content

Research Repository

Advanced Search

Evolutionary based Generative Adversarial Learning Approach to Metamorphic Malware Detection

People Involved

Project Description

Malicious attacks account for a significant portion of attacks to information assets and computer networks in organisations today. More specifically, dangerous groups of malware that transform their code structures between generations such as metamorphic malware, provide a greater attack surface for the perpetuation of cyber crimes. The detection of these malware family thus poses a challenge. Recent research show that Machine Learning (ML) techniques outperform traditional methods in detecting these dangerous malware groups. Hence, this research will involve the use of Evolutionary based Adversarial ML in defeating metamorphic malware.

Project Acronym EvoMalGAN
Status Project Complete
Funder(s) The Scottish Informatics & Computer Science Alliance
Value £1,200.00
Project Dates Jun 1, 2022 - Aug 31, 2022



You might also like

On the executability and malicious retention of adversarial malware samples generated using adversarial learning. Jan 27, 2023 - Jan 27, 2023
A SICSA Sponsored Research Theme Event
Machine Learning (ML) models have been shown to be vulnerable to adversarial examples designed to fool ML models to classify them as benign rather than malicious. This has led to several research efforts... Read More about On the executability and malicious retention of adversarial malware samples generated using adversarial learning..