Integration of Machine Learning with Data Science for Malware Detection

Authors

  • Sunita Choudhary, Anand Sharma

Abstract

These days, malwares have gotten increasingly complex and unsafe with the fast improvement of networks. Malwares like Trojan, virus denial-of-service (DoS) assaults are a difficult danger for network and computer security. Malware threats present new difficulties to analytic and reverse engineering errands. It is required for a systematic  methodology for malware detection, trying to completely reveal their basic assault vectors and procedures and discover shared characteristics between them. A solitary malware detection approach normally can't recognize some intricate assaults, for example, DoS assaults. This paper expects to propose and assess a malware identification approach with respect to the recognition of contamination assaults dependent on the perception in collaborative machine learning that each malware detection system may have various degrees of affectability in detecting explicit sorts of malware. The technique introduced in this work is a systematic and methodological interaction of malware detection, whose fundamental target is the acquisition of knowledge just as to acquire a full comprehension of a specific malware.

Published

2020-10-17

Issue

Section

Articles