Network traffic data privacy protection method and system

Abstract

The invention relates to the technical field of data protection, and discloses a network traffic data privacy protection method, which comprises the following steps of: receiving a network traffic data privacy protection instruction, and performing instruction verification on the network traffic data privacy protection instruction by utilizing an instruction verification algorithm based on a cachestrategy; acquiring corresponding network traffic data in the instruction according to the successfully verified network traffic data privacy protection instruction, and aggregating the network traffic data by using a K-means algorithm; utilizing a feature selection method based on interaction information to obtain a feature subset in the network flow data; obtaining abnormal network traffic datafeatures in the feature subset by using a cascaded random forest model, and deleting the abnormal network traffic data features; and according to the feature subset, performing privacy protection ofthe network traffic data by utilizing a data privacy protection algorithm based on random disturbance. The invention further provides a network traffic data privacy protection system. According to theinvention, the protection of private data is realized.

Description

technical field [0001] The present invention relates to the technical field of data protection, in particular to a method and system for protecting network traffic data privacy. Background technique [0002] With the rapid development of Internet technology, large-capacity storage technology and the gradual expansion of the scope of data sharing, the networking and transparency of data has become an irresistible trend. Data information generated by users in the network is frequently used for data mining. Network security issues such as privacy leaks emerge in an endless stream. Therefore, network data privacy protection in the big data environment has become an important research direction at present, and strives to achieve a balance between data availability and privacy security. [0003] The current data privacy protection technologies mainly include privacy protection technologies based on data anonymity and privacy protection technologies based on data distortion. Sele...

AI Technical Summary

Problems solved by technology

[0003] The current data privacy protection technologies mainly include privacy protection technologies based on data anonymity and privacy protection technologies based on data distortion. Selective release is carried out to achieve the purpose of reducing the risk of privacy leakage. Data anonymization is mainly to research and design effective anonymization rules, so that the data released using the anonymization rule can maintain its use value while protecting privacy. However, there is a certain degree of defect in the released data, which will cause a certain degree of data privacy leakage, and the cost of realizing optimized data anonymity is relatively large; the data distortion technology is to distort the data by adding random noise, thereby hiding the original data. In the data distortion method, on the one hand, the risk of privacy leakage is reduced by adding Laplacian noise to the original data; on the other hand, based on data exchange, new data is generated by transforming the original data, but at the same time It will change the statistical information of the original data, but this method will greatly reduce the mining accuracy of the distorted algorithm

[0004] At the same time, for the abnormal data existing in the network traffic data, the existing technology is mainly the isolation forest algorithm, in which the isolation forest algorithm establishes the abnormal index according to the path length from the leaf node to the root node, and the effect on the global abnormal point detection is better, but not Good at dealing with local relatively sparse points

Images