Research On Measurement Classification And Protection Methods Of Civil Aviation Passenger Sensitive Information

In recent years,my country’s civil aviation industry has developed rapidly,and more and more passengers travel by air.However,a lot of personal information of civil aviation passengers will be exposed during this period.In order to better serve civil aviation passengers,it is necessary to analyze and process their information.In order to realize the personalized service of civil aviation.In order to achieve this requirement,this paper proposes a privacy measurement and classification method to classify the privacy of civil aviation passengers,and according to the classification results,separate privacy protections for different sensitive levels.This targeted privacy protection saves time and space and improves efficiency.And it can improve the availability of data while protecting privacy.First of all,in order to solve the problem of difficult identification and protection of civil aviation passengers’ sensitive information,a method of civil aviation passenger privacy measurement and classification based on Shannon information entropy and support vector machine(SVM)is proposed.Based on the characteristics of civil aviation passenger data,a two-level privacy measurement element is established.Common data attributes(name,age,etc.)are called second-level elements,the second-level elements are mapped to the first-level elements,and Shannon information entropy is used to compare the second-level privacy elements.Measure,get the first-level privacy metric vector,and finally take the measurement result as input for SVM training,and output the grading result.According to the result,it has a higher accuracy rate.Secondly,in order to enable data managers to release data sets to researchers,so that researchers can mine and analyze data according to their needs,adopt differential privacy protection for data sets,but a lot of noise will be added to it,thereby destroying data availability.Therefore,a differential privacy civil aviation passenger data release algorithm based on clustering is proposed.Firstly,the clustering algorithm is improved.According to different data types,different distance calculation methods are selected for the numerical attributes and subtype attributes,which will be more likely to be related.The records are divided into a group to reduce the sensitivity of differential privacy.Combining the clusters formed by the clustering results,differential privacy protection technology is used to add noise to the data records.The experimental results show that it is possible to ensure the availability of data while protecting privacy from being leaked.