A Deep Learning Approach for Network Intrusion Detection Based on NSL-KDD Dataset

Along with the high-speed growth of Internet, cyber-attack is becoming more and more frequent, so the detection of network intrusions is particularly important for keeping network in normal work. In modern big data environment, however, traditional methods do not meet requirement of the network in the aspects of adaptability and efficiency. A approach based on deep learning for intrusion detection was proposed in this paper which can be applied to deal with the problem to certain extent. Autoencoder, as a popular technology of deep learning, was used in the proposed solution. The encoder of deep autoencoder was taken to compress the less important features and extract key features without decoder. With proposed approach one can build the network and identify attacks faster, the benchmark NSL-KDD dataset can be evaluated with proposed model.