Malware Detection Using Machine Learning Algorithms
Buddhadev Pusti
Malware, Malware detection, Portable Exe- cutable(PE) headers, Internet-connected devices, security
Malware is a critical security risk on Internet today. Malware is a set of programs designed to damage Internet- connected devices such as servers, computer resources, networks. Criminals are using Malware to send spam and to steal personal, financial, business information. Malware detection is the primary tool to stop unauthorized access of sensitive information. These days Windows OS is the most commonly used Operating System worldwide(77% to 88.8%) also it is the most targeted OS by malware attackers. In this paper detection of malware is done by simple observation of Portable Executable(PE) headers. In this paper, I use four methodology: 1. collect the data- set from 2. use an ExtraTreesClassifier for feature importance 3. use a ”most frequent” strategy for baseline model 4. use Random Forest classification algorithm as a benchmark model. My data-set contains 140849 benign samples and 75503 malware samples. In the data-set, the feature “legitimate” has values “0” and “1”, defines valid and malware files respectively. My experiments to detect malware by Portable Executable(PE) headers have a precision score of 98% and an f1-score of 98%. My experiments indicate that it is easy to detect malware files by observing Portable Executable(PE) headers.
Article Details
Unique Paper ID: 157797

Publication Volume & Issue: Volume 9, Issue 8

Page(s): 45 - 50
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews