Plausible Deniability for Privacy-Preserving Data Synthesis

被引:67
作者
Bindschaedler, Vincent [1 ]
Shokri, Reza [1 ]
Gunter, Carl A. [1 ]
机构
[1] UIUC, Champaign, IL USA
来源
PROCEEDINGS OF THE VLDB ENDOWMENT | 2017年 / 10卷 / 05期
基金
美国国家科学基金会;
关键词
D O I
10.14778/3055540.3055542
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Releasing full data records is one of the most challenging problems in data privacy. On the one hand, many of the popular techniques such as data de-identification are problematic because of their dependence on the background knowledge of adversaries. On the other hand, rigorous methods such as the exponential mechanism for differential privacy are often computationally impractical to use for releasing high dimensional data or cannot preserve high utility of original data due to their extensive data perturbation. This paper presents a criterion called plausible deniability that provides a formal privacy guarantee, notably for releasing sensitive datasets: an output record can be released only if a certain amount of input records are indistinguishable, up to a privacy parameter. This notion does not depend on the background knowledge of an adversary. Also, it can efficiently be checked by privacy tests. We present mechanisms to generate synt he tic data sets with similar statistical properties to the input data and the same format. We study this technique both theoretically and experimentally. A key theoretical result shows that, with proper randomization, the plausible deniability mechanism generates differentially private synthetic data. We demonstrate the efficiency of this generative technique on a large dataset; it is shown to preserve the utility of original data with respect to various statistical analysis and machine learning measures.
引用
收藏
页码:481 / 492
页数:12
相关论文
共 30 条
[1]  
[Anonymous], 2011, SYNTHETIC DATASETS S
[2]  
[Anonymous], 2003, LEARNING BAYESIAN NE
[3]  
[Anonymous], 2006, TCC
[4]  
[Anonymous], AM COMM SURV ACS
[5]  
[Anonymous], ACM SIGMOD
[6]  
[Anonymous], 2009, American Mathematical Soc.
[7]  
[Anonymous], 2011, JMLR
[8]  
[Anonymous], 2008, TAMC
[9]  
[Anonymous], 2007, TKDD
[10]  
[Anonymous], J OFFICIAL STAT