Study on network security intrusion target detection method in big data environment
Jia Chen, Yingkai Miao · International Journal of Internet Protocol Technology · 2021
In view of the traditional network security intrusion target detection method cannot effectively estimate the trend of the intrusion target, resulting in poor detection accuracy, a new network security intrusion target detection method under the big data environment is proposed. Set up under the environment of big data sequence model of network intrusion in the invasion of the information collected from different data centre, according to the binary feature of syntax tree for the intrusion information decomposition, the invasion of the target and get the feature sequences, with closed frequent search method, combining with the characteristics of sequence invasion of target extraction, using path, trends of binary weighted semantic of intrusion path direction get trend path set, exception path is obtained by covariance correction model trend estimation results, achieve network security intrusion detection. The experimental results show that this method has a better performance and better stability in the estimation of intrusion target path trend, with an estimated accuracy of between 94.9% and 98.6% and a detection time of 0.24-0.38 s.