Intrusion detection is an approach for providing a sense of security in
existing computer systems and data networks allowing them to operate in their
current “open" mode more securely. An intrusion detection system (IDS) inspects
all inbound and outbound network activities and identifies suspicious patterns that
may indicate a network or system attack from someone attempting to break into or
compromise the system. The goal of intrusion detection, then, is to identify,
preferably in real time, unauthorized use, misuse, and abuse of computer systems
and data networks by both system insides and external penetrators.
Nowadays new intelligent techniques have been used to improve the intrusion
detection process in computer networks. This paper presents an approach of an
adaptive multi-level intrusion detection and prevention system supported with a
hybrid intelligent system based on data mining for classification and pattern
recognition. We have specified attack signatures, reaction with event
communication and correlation that are integrated on the system, incorporating
supervised and unsupervised modes, and generating intelligent reasoning.