Flow Based Network Intrusion Detection System Using Hardware-Accelerated NetFlow Probes
Current network intrusion detection methods based on anomaly detection approaches suffer from comparatively higher error rate and low performance. Proposed flow based network intrusion detection system addresses these issues by using hardware-accelerated probes to collect unsampled NetFlow data from gigabit-speed network links and combining several anomaly detection algorithms by means of collective trust modeling, a multi-agent data fusion method. The data acquired on the network is preprocessed and passed to anomaly detection models to gather independent anomaly opinions for each flow. The anomaly data is passed to several trust models to aggregate the anomalies with past experience, and the flows are re-evaluated to obtain their trustfulness, which is further aggregated to detect malicious traffic.