arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.03458cs.CRcs.ITmath.IT
收藏

PAC隐私:数据处理的自动化隐私测量与控制

PAC Privacy: Automatic Privacy Measurement and Control of Data Processing

Hanshen Xiao, Srinivas Devadas

AI总结:

本研究提出PAC隐私这一基于实例的可模拟隐私度量,配套全自动分析框架可通过蒙特卡洛模拟为黑盒数据处理生成高置信安全参数,具备简洁组合性且扰动开销更低,突破了经典最坏情况隐私分析的局限。

摘要:

我们提出并研究了一种新的隐私定义,称为概率近似正确(Probably Approximately Correct,PAC)隐私。PAC隐私刻画了在任意处理过程中/处理后存在任意信息披露/泄露的情况下,恢复敏感数据在信息论层面的难度。与经典的密码学定义和差分隐私(Differential Privacy,DP)考虑对抗性的(与输入无关的)最坏情况不同,PAC隐私是一种可模拟的度量,量化了基于实例的推理不可能性。\n我们提出了一个全自动的分析与证明生成框架:对于任意黑盒数据处理预言机,可通过蒙特卡洛模拟以任意高置信度生成安全参数。这一极具吸引力的自动化特性能支持复杂数据处理的分析,而经典隐私体系下的最坏情况证明对这类处理可能过于宽松甚至难以求解。此外,我们证明生成的PAC隐私保证具备简洁的组合边界,且该自动化分析框架可在线实现,即使在相关随机性下也能分析组合式PAC隐私损失。\n在效用方面,对于d维发布结果,PAC隐私所需的(必要)扰动幅度不存在Theta(√d)的下界,在许多实际数据处理任务中可达到O(1),这与输入无关的最坏情况信息论下界形成对比。本文还包含PAC隐私的应用示例,并与现有研究进行了比较。

英文摘要:

We propose and study a new privacy definition, termed Probably Approximately Correct (PAC) Privacy. PAC Privacy characterizes the information-theoretic hardness to recover sensitive data given arbitrary information disclosure/leakage during/after any processing. Unlike the classic cryptographic definition and Differential Privacy (DP), which consider the adversarial (input-independent) worst case, PAC Privacy is a simulatable metric that quantifies the instance-based impossibility of inference. A fully automatic analysis and proof generation framework is proposed: security parameters can be produced with arbitrarily high confidence via Monte-Carlo simulation for any black-box data processing oracle. This appealing automation property enables analysis of complicated data processing, where the worst-case proof in the classic privacy regime could be loose or even intractable. Moreover, we show that the produced PAC Privacy guarantees enjoy simple composition bounds and the automatic analysis framework can be implemented in an online fashion to analyze the composite PAC Privacy loss even under correlated randomness. On the utility side, the magnitude of (necessary) perturbation required in PAC Privacy is not lower bounded by Theta(\sqrt{d}) for a d-dimensional release but could be O(1) for many practical data processing tasks, which is in contrast to the input-independent worst-case information-theoretic lower bound. Example applications of PAC Privacy are included with comparisons to existing works.

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。

↑