满足本地差分隐私的分类变换扰动机制

朱素霞; 王蕾; 孙广路

doi:10.7544/issn1000-1239.20200717

满足本地差分隐私的分类变换扰动机制

(哈尔滨理工大学计算机科学与技术学院哈尔滨 150080) (哈尔滨理工大学信息安全与智能技术研究中心哈尔滨 150080) (zhusuxia@hrbust.edu.cn)

基金项目: 国家自然科学基金项目(61502123)；黑龙江省留学归国人员科学基金项目(LC2018030)；黑龙江普通高校基本科研业务专项资金(JMRH2018XM04)；黑龙江省自然科学基金项目(LH2021F032)

详细信息

中图分类号: TP309
计量
- 文章访问数: 310
- HTML全文浏览量: 2
- PDF下载量: 127
出版历程
- 发布日期: 2022-01-31

A Perturbation Mechanism for Classified Transformation Satisfying Local Differential Privacy

(School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080) (Research Center of Information Security and Intelligent Technology, Harbin University of Science and Technology, Harbin 150080)

Funds: This work was supported by the National Natural Science Foundation of China (61502123), the Science Foundation for Returned Overseas Students of Heilongjiang Province (LC2018030), the Heilongjiang University Special Foundation for Basic Scientific Research (JMRH2018XM04), and the Natural Science Foundation of Heilongjiang Province (LH2021F032).

摘要

摘要: 本地差分隐私作为一种隐私保护技术，被广泛用于连续数值型数据的均值估计，使用的扰动机制将直接影响均值的准确度.为进一步提高均值估计的准确性，提出了一种满足差分隐私的分类变换扰动机制.该机制对连续数值型数据划分变换范围并进行分段，根据分段将其变换为1维二元分类数据.转换后使用随机响应机制进行扰动，再根据扰动后的数据标识的数值段从中随机均匀抽取数值作为扰动值.在真实数据和合成数据中的均值估计实验结果表明该机制极大地提高了准确性.除此之外，将分类变换扰动机制用于构建满足本地差分隐私的小批量梯度下降算法，并完成线性回归学习任务，实验结果证明该方法同样优于其他已有机制，可得到更小的均方误差.
- 本地差分隐私 /
- 数据转换 /
- 均值估计 /
- 小批量梯度下降 /
- 随机响应
Abstract: As the state-of-the-art privacy protection technology, local differential privacy is widely used to compute the mean value of continuous numerical data. The perturbation mechanism will directly affect the accuracy of the mean value. In order to further improve the accuracy of mean value estimation, a perturbation mechanism for classified transformation satisfying differential privacy is proposed. In this mechanism, continuous numerical data is divided into transformation range, which is then segmented. What’s more, it transforms the segmentation into one-dimensional binary category data. After transformation, the mechanism of random response is used to perturb the data. More importantly, it extracts the value randomly as well as uniformly from the numerical segment identified by the perturbation data as the perturbed value. The experimental results of mean value estimation in both real data and synthetic data show that the mechanism proposed in the paper greatly improves the accuracy. In addition, this perturbation mechanism is used to build a mini-batch gradient descent algorithm satisfying local differential privacy and the linear regression learning task is completed successfully. The experimental results show that this method not only is superior to other existing mechanisms but also can obtain a smaller mean square error at the same time.
- local differential privacy /
- data transformation /
- mean value estimation /
- mini-batch gradient descent /
- random response

HTML全文

参考文献(0)

施引文献(9)

期刊类型引用(4)

1.	陈亮. 道路网格网模式识别的关键指标设计. 测绘与空间地理信息. 2024(01): 193-195+199 . 百度学术
2.	张勇飞，陈艳君，赵世忠. 引入神经网络极限学习机的关键数据查询模型. 计算机仿真. 2024(03): 519-523 . 百度学术
3.	轩瑞，陈磊，石海鹤. 图类算法可重用设计及其实现. 江西师范大学学报(自然科学版). 2023(01): 52-60 . 百度学术
4.	丁莹莹，卜昌森，连会青，尹尚先，徐斌，张丐卓，姚辉，董其金. 基于仿真平台的矿井突水淹没路径和逃生路径规划. 煤矿安全. 2023(05): 20-26 . 百度学术