Yixuan Liu, Yuhan Liu, Li Xiong, Yujie Gu, Hong Chen
{"title":"增强洗牌模型的个性化隐私约束","authors":"Yixuan Liu, Yuhan Liu, Li Xiong, Yujie Gu, Hong Chen","doi":"arxiv-2407.18157","DOIUrl":null,"url":null,"abstract":"The shuffle model of Differential Privacy (DP) is an enhanced privacy\nprotocol which introduces an intermediate trusted server between local users\nand a central data curator. It significantly amplifies the central DP guarantee\nby anonymizing and shuffling the local randomized data. Yet, deriving a tight\nprivacy bound is challenging due to its complicated randomization protocol.\nWhile most existing work are focused on unified local privacy settings, this\nwork focuses on deriving the central privacy bound for a more practical setting\nwhere personalized local privacy is required by each user. To bound the privacy\nafter shuffling, we first need to capture the probability of each user\ngenerating clones of the neighboring data points. Second, we need to quantify\nthe indistinguishability between two distributions of the number of clones on\nneighboring datasets. Existing works either inaccurately capture the\nprobability, or underestimate the indistinguishability between neighboring\ndatasets. Motivated by this, we develop a more precise analysis, which yields a\ngeneral and tighter bound for arbitrary DP mechanisms. Firstly, we derive the\nclone-generating probability by hypothesis testing %from a randomizer-specific\nperspective, which leads to a more accurate characterization of the\nprobability. Secondly, we analyze the indistinguishability in the context of\n$f$-DP, where the convexity of the distributions is leveraged to achieve a\ntighter privacy bound. Theoretical and numerical results demonstrate that our\nbound remarkably outperforms the existing results in the literature.","PeriodicalId":501123,"journal":{"name":"arXiv - CS - Databases","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhanced Privacy Bound for Shuffle Model with Personalized Privacy\",\"authors\":\"Yixuan Liu, Yuhan Liu, Li Xiong, Yujie Gu, Hong Chen\",\"doi\":\"arxiv-2407.18157\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The shuffle model of Differential Privacy (DP) is an enhanced privacy\\nprotocol which introduces an intermediate trusted server between local users\\nand a central data curator. It significantly amplifies the central DP guarantee\\nby anonymizing and shuffling the local randomized data. Yet, deriving a tight\\nprivacy bound is challenging due to its complicated randomization protocol.\\nWhile most existing work are focused on unified local privacy settings, this\\nwork focuses on deriving the central privacy bound for a more practical setting\\nwhere personalized local privacy is required by each user. To bound the privacy\\nafter shuffling, we first need to capture the probability of each user\\ngenerating clones of the neighboring data points. Second, we need to quantify\\nthe indistinguishability between two distributions of the number of clones on\\nneighboring datasets. Existing works either inaccurately capture the\\nprobability, or underestimate the indistinguishability between neighboring\\ndatasets. Motivated by this, we develop a more precise analysis, which yields a\\ngeneral and tighter bound for arbitrary DP mechanisms. Firstly, we derive the\\nclone-generating probability by hypothesis testing %from a randomizer-specific\\nperspective, which leads to a more accurate characterization of the\\nprobability. Secondly, we analyze the indistinguishability in the context of\\n$f$-DP, where the convexity of the distributions is leveraged to achieve a\\ntighter privacy bound. Theoretical and numerical results demonstrate that our\\nbound remarkably outperforms the existing results in the literature.\",\"PeriodicalId\":501123,\"journal\":{\"name\":\"arXiv - CS - Databases\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Databases\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.18157\",\"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 - CS - Databases","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.18157","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Enhanced Privacy Bound for Shuffle Model with Personalized Privacy
The shuffle model of Differential Privacy (DP) is an enhanced privacy
protocol which introduces an intermediate trusted server between local users
and a central data curator. It significantly amplifies the central DP guarantee
by anonymizing and shuffling the local randomized data. Yet, deriving a tight
privacy bound is challenging due to its complicated randomization protocol.
While most existing work are focused on unified local privacy settings, this
work focuses on deriving the central privacy bound for a more practical setting
where personalized local privacy is required by each user. To bound the privacy
after shuffling, we first need to capture the probability of each user
generating clones of the neighboring data points. Second, we need to quantify
the indistinguishability between two distributions of the number of clones on
neighboring datasets. Existing works either inaccurately capture the
probability, or underestimate the indistinguishability between neighboring
datasets. Motivated by this, we develop a more precise analysis, which yields a
general and tighter bound for arbitrary DP mechanisms. Firstly, we derive the
clone-generating probability by hypothesis testing %from a randomizer-specific
perspective, which leads to a more accurate characterization of the
probability. Secondly, we analyze the indistinguishability in the context of
$f$-DP, where the convexity of the distributions is leveraged to achieve a
tighter privacy bound. Theoretical and numerical results demonstrate that our
bound remarkably outperforms the existing results in the literature.