NETWORK INTRUSION DETECTION BASED ON CLASIFICATION

Abstract

Network security is a serious concern for information technology users. Intrusion detection systems can detect malicious traffic and suspicious activity looking for signatures of known attacks. This paper describes a network intrusion detection system based on deep-learning approach. The system uses the ability of the convolutional neural network to detect attacks for which the system was not explicitly trained. The proposed solution can effectively identify network attacks with accuracy of 98% on the KDD99 dataset.