标签差异隐私的对立面:PATE和ALIBI
Antipodes of Label Differential Privacy: PATE and ALIBI
摘要:
我们考虑隐私保护机器学习(ML)设置,其中训练模型必须满足训练样本标签的差分隐私(DP)。我们提出了两种新的方法的基础上,分别拉普拉斯机制和PATE框架,并证明其有效性的标准基准。虽然Ghazi等人最近的工作提出了基于随机响应机制的标签DP方案,但我们认为加性拉普拉斯噪声加上贝叶斯推理(ALIBI)更适合典型的ML任务。此外,我们展示了如何在某些制度中实现非常强大的隐私级别,我们适应的PATE框架,建立在半监督学习的最新进展。我们补充我们的算法的隐私保证与经验评估其记忆性能的理论分析。我们的评估表明,比较不同的算法,根据其可证明的DP保证可能会产生误导,有利于一个更严格的分析,更少的私人算法。用于实现算法和记忆攻击的代码可从www.example.com获得。
英文摘要:
We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples. We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks. While recent work by Ghazi et al. proposed Label DP schemes based on a randomized response mechanism, we argue that additive Laplace noise coupled with Bayesian inference (ALIBI) is a better fit for typical ML tasks. Moreover, we show how to achieve very strong privacy levels in some regimes, with our adaptation of the PATE framework that builds on recent advances in semi-supervised learning. We complement theoretical analysis of our algorithms' privacy guarantees with empirical evaluation of their memorization properties. Our evaluation suggests that comparing different algorithms according to their provable DP guarantees can be misleading and favor a less private algorithm with a tighter analysis. Code for implementation of algorithms and memorization attacks is available from https://github.com/facebookresearch/label_dp_antipodes.
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。