Abstract: In this we propose an effective intrusion detection system for improving the detection accuracy. In this proposed system, we propose a new feature selection algorithm called enhanced cuttlefish feature selection algorithm (ECFSA) for effective feature selection and Intelligent Agent based Enhanced Multiclass Support Vector Machine (IAEMSVM) classification algorithm is used for classification. The experimental results of the proposed system show that this system produced high-detection rate when tested with KDD cup 99 dataset.

Keywords: CRF – Conditional Random Field, CuttleFish Feature Selection, Multiclass Support Vector Machine.