arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.20546cs.LG
收藏

可预测性作为隐私的细粒度度量

Predictability as a Fine-Grained Measure for Privacy

Cornell University(康奈尔大学)

Linda Lu, Karthik Sridharan

AI总结:

提出可预测性框架,通过攻击者预测敏感信息的能力增益来衡量隐私泄露,与差分隐私互补,并基于广义矩方法分析渐近可预测性,用于ERM输出扰动。

摘要:

差分隐私(DP)确保针对最知识渊博的攻击者的严格个体级隐私保证,但其最坏情况性质可能导致代价高昂的隐私-准确性权衡。我们引入了通过可预测性实现的隐私,这是一个细粒度框架,明确包含了攻击者的核心知识、由随机过程生成的数据集的受损部分以及指定的查询族。可预测性将隐私泄露衡量为攻击者在观察算法输出后,预测关于未知个体的敏感信息的能力的增量增益,超出已从受损数据中推断出的信息。我们表明,可预测性和DP通常是不可比的:一个可以很小而另一个很大。然而,在最坏情况下,当除一个个体外所有个体都受损且所有二元查询都被视为敏感时,可预测性意味着互信息DP。更一般地,可预测性提供了一种针对特定敏感信息和特定攻击者模型量身定制的更细粒度的隐私度量。我们引入了一个通用框架,使用广义矩方法(GMM),来分析当受损数据由平稳、遍历、混合过程生成时的渐近可预测性。利用这一分析,我们推导出用于ERM的可预测性校准输出扰动方案。我们的方法与DP互补,并且可以与DP一起使用以提供细粒度的隐私控制。

英文摘要:

Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-accuracy tradeoff. We introduce privacy via predictability, a fine-grained framework that explicitly incorporates the attacker's core knowledge, a compromised portion of the dataset generated by a stochastic process, and a specified family of queries. Predictability measures privacy leakage as the incremental gain in an attacker's ability to predict sensitive information about unknown individuals after observing the algorithm's output, beyond what can already be inferred from the compromised data. We show that predictability and DP are generally incomparable: each can be small while the other is large. However, in the worst-case regime where all but one individual is compromised, and all binary queries are considered sensitive, predictability implies mutual-information DP. More generally, predictability provides a finer-grained privacy metric tailored to specific sensitive information and specific attacker models. We introduce a general framework, using the generalized method of moments (GMM), to analyze asymptotic predictability when the compromised data is generated by a stationary, ergodic, mixing process. Using this analysis, we derive a predictability-calibrated output perturbation scheme for ERM. Our approach is complementary to DP and can be used alongside DP to provide fine-grained privacy control.

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。

↑