An Efficient Intrusion Detection and Prevention System against Insider Attack by User Behavior Mining

Abstract

Intrusion Detection Systems (IDS) plays a significant role in computer security. In network surroundings IDS find the activities that have an effect on Confidentiality, Integrity and accessibility on network knowledge. Currently, most computer systems use user IDs and passwords because the login patterns to certify users. However, many of us share their login patterns with coworkers and request these coworkers to help co-tasks, thereby creating the pattern united of the weakest points of computer security. Insider attackers, the valid users of a system who attack the system internally, are exhausting to find since most intrusion detection systems and firewalls establish and isolate malicious behaviors launched from the external world of the system solely. Additionally, some studies claimed that analyzing system calls (SCs) generated by commands will establish these commands, with that to accurately find attacks, with attack patterns are the options of an attack. Therefore, during this paper, a security system, named the interior Intrusion Detection and Protection System (IIDPS), is projected to find Insider attacks at SC level by victimization data processing and rhetorical techniques. The IIDPS creates users’ personal profiles to stay track of users’ usage habits as their rhetorical options and determines whether or not a sound login user is that the account holder or not by scrutiny his/her current laptop usage behaviors with the patterns collected within the account holder’s personal profile.