Layered security architecture for masquerade attack detection

摘要: Masquerade attack refers to an that uses a fake identity, gain unauthorized access personal computer information through legitimate identification. Automatic discovery of masqueraders is sometimes undertaken by detecting significant departures from normal user behavior. If user's profile deviates their original behavior, it could potentially signal ongoing masquerade attack. In this paper we proposed new framework capture data in comprehensive manner collecting different layers across multiple applications. Our approach generates feature vectors which contain the output gained analysis such as Window Data, Mouse Keyboard Command Line File Access Data and Authentication Data. We evaluated our several experiments with number participants. experimental results show better detection rates acceptable false positives none earlier approaches has achieved level accuracy so far.