Network Intrusion Risk Assessment Based on Big Data
Qing Ye Li · 2019
The accurate evaluation of network intrusion risk big data, improve the evaluation probability is the basis to ensure the network security, the traditional evaluation method is difficult to realize the efficient location and evaluation of the network intrusion data under the strong intrusion interference. It cannot effectively evaluate the global feature points of the regular data of network intrusion association, which leads to high probability of resampling, false alarm and missed detection. A network intrusion risk assessment algorithm based on big data association rule mining is proposed to construct a network intrusion risk big data model under strong intrusion interference. The fuzzy search method of network intrusion correlation dimension feature is used to search the regular data of network intrusion association adaptively, and the global feature evaluation and intrusion intensity evaluation value of network intrusion association regularization data are obtained. In order to make intrusion evaluation suitable for linear real-time processing process and improve the performance of evaluation under strong intrusion interference, a stochastic linear fitting model is used to adjust the results. Big data association rules mining is used to judge the joint characteristics of network intrusion association regularization data and realize the mining and risk assessment of network intrusion big data association rules. The simulation results show that the algorithm has better performance in intrusion risk assessment, and the evaluation probability is better than the traditional algorithm, which ensures the network security.