Arrangement and capturing of malevolent packets in network using machine learning
Rakesh Kumar Yadav, R Raghavendra, Amit Barve · 2024
The importance of cyber security and cyber warfare has grown in a world where digitalization is rapidly expanding and developing. Malware, or malicious software, has emerged as a major problem in the modern digital age. The rapid proliferation of malware is a major danger to online safety. Therefore, steps taken to secure the network are crucial in warding off these cyber dangers. Using a network analyzer to gather instances of botched and artificially created benign packets, the authors of the current paper collected data for a network traffic classifier using a random forest (RF) machine learning approach. The suggested classifier can determine whether or not a given piece of traffic (HTTP, TCP, UDP, IPv4-v6) is safe to proceed with. The experimental findings show that the suggested model using the RF classifier is more accurate than the baseline.