Fusion of Machine Learning Algorithms for Comprehensive Malware Detection and Analysis

Fusion of Machine Learning Algorithms for Comprehensive Malware Detection and Analysis

M.Buvaneswari #1,G . Swathi #2,S.Sandhiya #3, T. SelvaKumar #4,

R.PraveenKumar #5

 Department of Computer Science and Engineering, Muthayammal Engineering College

buvan.jeynesh@gmail.com

swathi582003@gmail.com

sandhiyaselvam2012@gmail.com

selvakumar.toffical@gmail.com

ravisri0123praveen@gmail.com

Abstract
Malware has emerged as a significant cyberthreat that impacts both individuals and organisations due to the Internet's explosive expansion. Any software that damages computer systems or steals personal information is considered malware. Regular antivirus software is no longer sufficient to completely defend against attacks since malware is constantly changing. According to a 2015 assessment by a prominent cybersecurity firm, 4 million distinct malware threats were found across six different platforms. According to Juniper Research, data breaches would cost the global economy $2.1 trillion by 2019. The ease with which hacking tools can now be found online contributes to the increase in cyberthreats by enabling even inexperienced individuals to produce and disseminate malware. Additionally, a lot of attackers purchase software from illicit sources, which raises the frequency of intrusions. Research indicates that an increasing number of attacks are carried out automatically or by novices, referred to as "script-kiddies." Better security measures, more intelligent malware detection techniques, and greater awareness are all necessary to protect against cyberattacks, as this expanding threat makes clear.

Keywords— Malware detection, Machine learning, Random Forest, K-Means clustering, Cybersecurity, Threat analysis.