In the process of network intrusion detection, the network operating data need to be counted. Then, the network intrusion detection can be performed through comparing the values of the statistical results with the threshold values of network intrusion detection sequentially. However, too large network operating data will cause the overlapping of operating data during the detection, reducing the accuracy of the network intrusion detection. In order to avoid the defect mentioned above, a large data network intrusion detection algorithm introduced with quantum optimization neural network is proposed. Through the analysis of the principal component of the data, the process of the massive network operating data can be simplified. Using the quantum neural network method, the initial threshold of network intrusion feature can be achieved, so as to provide accurate data base for the network intrusion detection. Taking the advantage of small distance parade of genetic algorithms, the threshold characteristic is optimized and the mass redundancy interference characteristic is overcome, so as to fulfill the network intrusion detection. Experimental results show that the proposed algorithm used for network intrusion detection can improve the accuracy of detection effectively and achieve satisfactory results.
An improved bayesian network intrusion detection algorithm based on deep learning
