arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09680cs.CR
收藏

面向稀疏Lipschitz函数的可认证隐私数据发布

Certified private data release for sparse Lipschitz functions

Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang

AI总结:

针对机器学习训练数据隐私保护及预定义查询未知等场景,提出面向稀疏Lipschitz查询的快速效用损失收敛隐私算法,并实现大类算法的效用损失认证。

摘要:

随着机器学习在日常应用中的相关性日益提升,训练数据的隐私保护成为一项自然需求。当相关学习问题预先未知,或超参数调优占据核心地位时,一种解决方案是发布差分隐私合成数据集,其能得出与原始训练数据相似的结论。本研究提出一种算法,在稀疏Lipschitz查询下具备快速的效用损失收敛速率。此外,我们展示了如何为一大类算法获取效用损失的认证证书。

英文摘要:

As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.

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。

↑