Malware Traffic Analysis using Machine Learning

Malware refers to computer code or software that is installed and operated on a user's computer or other terminal without explicit notification or permission, engaging in activities such as stealing, encrypting, modifying, and deleting data, and monitoring the legitimate rights and interests of users. The types of malwares include viruses, worms, Trojans, ransomware, spyware, and so on. Different types of malwares have different attack methods and can cause different damages, resulting in potential financial losses for users. Five machine learning algorithms were used to conduct comparative analysis and find the best performing model to predict potential malware traffic issues in networks. We used the CIC-IDS-2017 dataset, Pearson correlation coefficient to select features and 5-fold cross validation to evaluate the model's generalization ability.