HIDS with minimize property

Abstract

Security system is the immune system for computers which is similar to the immune system in the human body. This includes all operations required to protect computer and systems from intruders. The aim of this paper is to develop an anomaly-based intrusion detection system (IDS) that can promptly detect and classify various attacks. Anomalybased IDSs need to be able to learn the dynamically changing behavior of users or systems. In this paper are experimenting with packet behavior as parameters in anomaly intrusion detection. There are several methods to assist IDSs to learn system's behavior. The proposed IDS use a back propagation artificial neural network (ANN) to learn system's behavior. A new operation has been added to this work by minimize the property of packet from 22 properties to 4 main properties. The KDD'99 data set had been used in the experiments and the obtained results satisfy the work objective