An Investigation to Detect Banking Malware Network Communication Traffic Using Machine Learning Techniques

Banking malware are malicious programs that attempt to steal confidential information, such as banking authentication credentials, from users. Zeus is one of the most widespread variants ever discovered. Since source code was leaked, many other have emerged, and tools anti-malware exist can detect Zeus; however, these limitations. Anti-malware need be regularly updated recognise Zeus, signatures or patterns only made available when has been seen. This limits capability products because they unable unseen variants, furthermore, users developing seeks evade signature-based programs. In this paper, a methodology proposed for detecting network traffic flows by using machine learning (ML) binary classification algorithms. research explores compares several ML algorithms determine algorithm best suited problem then uses conduct further experiments minimum number features could used malware. also suitability both older newer versions well additional will help researchers understand which flow whether work across multiple