Improving Network Intrusion Detection Through Classifier Combination

Network intrusion detection is a problem that’s hardly being solved completely. Firewalls and other existing solutions do provide some resistance to the wide variety of attack types that can occur, but they suffer the drawback of not being able to generalize well into unseen attack types. Through this report, we propose a framework for addressing the problem of network intrusion by extracting ideas from the machine learning community. Specifically, we focus on ensemble methods where multiple schemes are joined to do a better job at predicting malicious connections. With this approach, we propose that malicious connections can be predicted with high precision and high confidence.