Explaining Differentially Private Query Results With DPXPlain
Explaining Differentially Private Query Results With DPXPlain
复制标题
DOI：
10.14778/3611540.3611596
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Tingyu Wang;Yuchao Tao;Amir Gilad;Ashwin Machanavajjhala;Sudeepa Roy
中科院分区：
文献类型：
--
作者：
Tingyu Wang;Yuchao Tao;Amir Gilad;Ashwin Machanavajjhala;Sudeepa Roy
采用差分隐私（DP），最先进的隐私标准，回答聚合数据库查询提出了新的挑战，为用户了解的趋势和异常观察到的查询结果：是由于数据本身的意外答案，还是由于额外的噪音，必须添加以保持DP？我们建议演示DPXPlain，第一个系统解释组聚合查询答案DP。DPXPlain允许用户比较两组的值并接受有效性检查，并进一步提供具有交互式可视化的解释表，包含近似“前k”解释谓词沿着相对影响和置信区间形式的排名，同时保证所有步骤中的DP。
Employing Differential Privacy (DP), the state-of-the-art privacy standard, to answer aggregate database queries poses new challenges for users to understand the trends and anomalies observed in the query results: Is the unexpected answer due to the data itself, or is it due to the extra noise that must be added to preserve DP? We propose to demonstrate DPXPlain, the first system for explaining group-by aggregate query answers with DP. DPXPlain allows users to compare values of two groups and receive a validity check, and further provides an explanation table with an interactive visualization, containing the approximately 'top-k' explanation predicates along with their relative influences and ranks in the form of confidence intervals, while guaranteeing DP in all steps.