The article addresses the pressing issue of obfuscated malware, which evades traditional detection systems due to its ability to hide effectively. Conventional heuristic and signature-based systems often fail at identifying such threats, highlighting the need for innovative approaches. This study proposes a memory dump analysis method leveraging various machine learning algorithms, including decision trees and ensemble methods, tested on the CIC-MalMem-2022 dataset. The research evaluates these algorithms' effectiveness in detecting obfuscated malware, providing insights into their strengths and weaknesses. The findings aim to bolster cybersecurity measures and make the source code open access for future research.
In the era of the internet and smart devices, detection of malware is crucial for system security as malware authors use obfuscation to elude detection.
This research proposes a cost-effective obfuscated malware detection system through memory dump analysis, leveraging diverse machine learning algorithms for enhanced detection.
Our study evaluates the effectiveness of algorithms, such as decision trees and neural networks, in detecting obfuscated malware within memory dumps.
This paper contributes to enhancing cybersecurity by offering a comprehensive assessment of machine learning algorithms for detecting sophisticated obfuscated malware threats.
Collection
[
|
...
]