INTRUSION PREVENTION IN NETWORK USING SUPERVISED DEEP LEARNING
A Convolution Neural Network based Deep learning system is come about to classify network traffic whether it is malware or benevolent. To find the best model considering detection success rate, a mixture of supervised learning algorithm and feature selection method have been used. Through this system, it is found that Deep learning with wrapper feature selection do better than Decision Trees algorithm while classifying network traffic.
To evaluate the performance of this intrusion prevention system a NSL-KDD dataset is used. It is an effective benchmark data set used to classify network traffic using Convolution Neural Network Deep learning techniques to obtain whether the connected node is malicious or not. Comparative system shows that the proposed model is efficient than other existing models with respect to intrusion detection success rate.