arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.02562cs.LGcs.CRcs.DBstat.ML
收藏

基于敏感性采样的无痛随机差分隐私

Pain-Free Random Differential Privacy with Sensitivity Sampling

University of Melbourne(墨尔本大学);Ruhr-Universität Bochum(波鸿鲁尔大学)

Benjamin I. P. Rubinstein, Francesco Aldà

摘要:

差分隐私的流行方法,如拉普拉斯和指数机制,通过目标非私有函数的全局敏感性来校准随机平滑。限制这种灵敏度通常是非常复杂的分析计算。作为一种替代方案,我们提出了一个简单的采样估计非私有机制的敏感性。由于我们的敏感性估计以高概率成立,因此在有界全局敏感性下将是$(ε,δ)$ -差分隐私的任何机制自动实现$(ε,δ,γ)$ -随机差分隐私(Hall等人,2012年),不需要任何具体目标的计算。我们演示工作的例子学习者如何使用我们的方法采用自然放松的隐私保证,同时实现更准确的释放,即使是非私人功能的黑盒计算机程序。

英文摘要:

Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively complex analytic calculation. As an alternative, we propose a straightforward sampler for estimating sensitivity of non-private mechanisms. Since our sensitivity estimates hold with high probability, any mechanism that would be $(ε,δ)$-differentially private under bounded global sensitivity automatically achieves $(ε,δ,γ)$-random differential privacy (Hall et al., 2012), without any target-specific calculations required. We demonstrate on worked example learners how our usable approach adopts a naturally-relaxed privacy guarantee, while achieving more accurate releases even for non-private functions that are black-box computer programs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑