A novel approach for intrusion detection using KNN classification and DS-Theory

Abstract

Intrusion detection is a very challenging area of research in a current scenario. Now every day find a new pattern of intrusion and
detection of this pattern are very challenging job. In this paper we have discuss a novel approach for intrusion detection using KNN
classification and Dempester theory of evidence. Through these approaches gathered a new discovered pattern of intrusion and classify
Category of pattern and apply event evidence logic with the help of DS- Theory. Finned pattern of intrusion compare with the existing pattern if
intrusion and generate a new schema of pattern and update a list of pattern of intrusion detection and improved the true rate of intrusion
detection. we have also perform some experimental task with KDD99Cup and DARPA98 databases from MIT Lincoln Laboratory show that
the proposed method provides competitively high detection rates compared with other machine-learning techniques and crisp data mining

Keywords:-intrusion Detection, KNN, DS-Theory