High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Accessing Rarity of System Call Patterns for Anomaly Detection

Author(s):

Kulkarni Sagar Suresh , SPCOE, otur ; Kahate Sandip, SPCOE,otur

Keywords:

Anomaly Detection; Intrusion Detection; Semantic Theory

Abstract

Today computer security is important field research because more and more security threats arising in daily basis. Many researches focus on use intrusion detection system so as to prevent these intrusions. But most of the intrusion detection system suffers from high FPR and TPR. This is because of incomplete training and strategy used by them for detecting suspicious behaviour. This paper presents a host based intrusion detection that uses natural language concepts and rarity index to find anomalous system call trace. Also proposed system uses approximate pattern matching over mismatched sequence to defend against incomplete training. Evaluation of proposed is carried using publicly available UNM intrusion detection dataset. The results support the proposed system.

Other Details

Paper ID: IJSRDV3I31301
Published in: Volume : 3, Issue : 3
Publication Date: 01/06/2015
Page(s): 2083-2086

Article Preview

Download Article