THE DEVELOPMENT OF CLASSIFIER ENSEMBLES FOR INTRUSION DETECTION IN NETWORK SECURITY
|
|
Nowadays an increasing number of commercial and public services are offered through Internet, so that security is becoming one of the key issues. The so-called "attacks" to internet service providers are carried out by exploiting unknown weaknesses or bugs always contained in system and application software. Computer networks are usually protected against attacks by a number of access restriction policies that act as a coarse grain filter. Intrusion detection systems (IDS) are the fine grain filter placed inside the protected network, looking for known or potential threats in network traffic and/or audit data recorded by hosts. Researchers recently proposed intrusion detection approaches based on pattern recognition algorithms trained on malicious and normal traffic activities. This formulation of intrusion detection problem combines the advantages of signature-based and anomaly-based IDS. It allows designing decision “boundaries” between normal and malicious network traffic. In this project, an approach to intrusion detection in computer networks based on multiple classifier systems will be studied. This approach is motivated by the observation that generally a combination of classifiers performs better than a single classifier. Hence, we will study the use of classifier ensemble to predict intrusion detection.
|