Test Suite for Intrusion Detection by Layered Conditional Random Fields Using Mobile Phones

Abstract

There is high demand to reduce the threat level in networks to ensure the data and services offered by them to be more secure. With the ever increasing number and diverse type of attacks, including new and previously unseen attacks, the effectiveness of an Intrusion Detection System is very important. Earlier works deal with the layered approach and conditional random fields (CRFs) for improving the efficiency and accuracy of an intrusion detection system. In this paper we developed an effective test suite using the layered CRFs. We set up different types of checks at multiple levels in each layer. Our framework examines various attributes at every layer in order to effectively identify any breach of security. Once the attack is detected, it is intimated through mobile phone to the system administrator for safe guarding the server system. We establish experimentally that the layered CRFs can be very effective in detecting intrusions when compared with the previously known techniques.