{"title":"利用贝叶斯非参数分层模型进行信息披露风险评估","authors":"Marco Battiston, Lorenzo Rimella","doi":"arxiv-2408.12521","DOIUrl":null,"url":null,"abstract":"Micro and survey datasets often contain private information about\nindividuals, like their health status, income or political preferences.\nPrevious studies have shown that, even after data anonymization, a malicious\nintruder could still be able to identify individuals in the dataset by matching\ntheir variables to external information. Disclosure risk measures are\nstatistical measures meant to quantify how big such a risk is for a specific\ndataset. One of the most common measures is the number of sample unique values\nthat are also population-unique. \\cite{Man12} have shown how mixed membership\nmodels can provide very accurate estimates of this measure. A limitation of\nthat approach is that the number of extreme profiles has to be chosen by the\nmodeller. In this article, we propose a non-parametric version of the model,\nbased on the Hierarchical Dirichlet Process (HDP). The proposed approach does\nnot require any tuning parameter or model selection step and provides accurate\nestimates of the disclosure risk measure, even with samples as small as 1$\\%$\nof the population size. Moreover, a data augmentation scheme to address the\npresence of structural zeros is presented. The proposed methodology is tested\non a real dataset from the New York census.","PeriodicalId":501215,"journal":{"name":"arXiv - STAT - Computation","volume":"9 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Disclosure risk assessment with Bayesian non-parametric hierarchical modelling\",\"authors\":\"Marco Battiston, Lorenzo Rimella\",\"doi\":\"arxiv-2408.12521\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Micro and survey datasets often contain private information about\\nindividuals, like their health status, income or political preferences.\\nPrevious studies have shown that, even after data anonymization, a malicious\\nintruder could still be able to identify individuals in the dataset by matching\\ntheir variables to external information. Disclosure risk measures are\\nstatistical measures meant to quantify how big such a risk is for a specific\\ndataset. One of the most common measures is the number of sample unique values\\nthat are also population-unique. \\\\cite{Man12} have shown how mixed membership\\nmodels can provide very accurate estimates of this measure. A limitation of\\nthat approach is that the number of extreme profiles has to be chosen by the\\nmodeller. In this article, we propose a non-parametric version of the model,\\nbased on the Hierarchical Dirichlet Process (HDP). The proposed approach does\\nnot require any tuning parameter or model selection step and provides accurate\\nestimates of the disclosure risk measure, even with samples as small as 1$\\\\%$\\nof the population size. Moreover, a data augmentation scheme to address the\\npresence of structural zeros is presented. The proposed methodology is tested\\non a real dataset from the New York census.\",\"PeriodicalId\":501215,\"journal\":{\"name\":\"arXiv - STAT - Computation\",\"volume\":\"9 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.12521\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.12521","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Disclosure risk assessment with Bayesian non-parametric hierarchical modelling
Micro and survey datasets often contain private information about
individuals, like their health status, income or political preferences.
Previous studies have shown that, even after data anonymization, a malicious
intruder could still be able to identify individuals in the dataset by matching
their variables to external information. Disclosure risk measures are
statistical measures meant to quantify how big such a risk is for a specific
dataset. One of the most common measures is the number of sample unique values
that are also population-unique. \cite{Man12} have shown how mixed membership
models can provide very accurate estimates of this measure. A limitation of
that approach is that the number of extreme profiles has to be chosen by the
modeller. In this article, we propose a non-parametric version of the model,
based on the Hierarchical Dirichlet Process (HDP). The proposed approach does
not require any tuning parameter or model selection step and provides accurate
estimates of the disclosure risk measure, even with samples as small as 1$\%$
of the population size. Moreover, a data augmentation scheme to address the
presence of structural zeros is presented. The proposed methodology is tested
on a real dataset from the New York census.