Malware Detection and Analysis using Machine Learning
Manoj Sirigiri, Divya Sirigiri, Rajshri Aishwarya, R. Yogitha · 2023
Online privacy for people is getting worse every day. Computer malware is tainting the data records of some well-known companies. Hackers can gain access to a network and change data, once inside. This work discusses several types of malware and communication strategies, such as Trojans, keyloggers, port forwarding, source code obfuscation, application format converters, and social engineering techniques. Three different machine learning algorithms are applied in this work to derive meaningful insights from the data. As a result of the work proposed, given malware can be categorized as a malicious or a non-malicious application. This is executed by analyzing the classification report, accuracy and f1 score metrics. The Random Forest is selected as a champion model based on the highest f'1-score for the validation dataset.