arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.03604quant-phcs.CRcs.DScs.LG
收藏

量子与量子启发式算法中的差分隐私放大

Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms

LIP6(LIP6实验室);CNRS(法国国家科学研究中心);Sorbonne Université(索邦大学);School of Informatics, University of Edinburgh(爱丁堡大学信息学院)

Armando Angrisani, Mina Doosti, Elham Kashefi

AI总结:

本研究针对量子与量子启发式算法展开,首次证明经典数据集量子编码上的算法及量子启发式经典采样结果可放大幅分隐私,同时验证了满足混合条件的量子信道组合可放大量子差分隐私,给出了对应隐私放大边界。

摘要:

差分隐私为处理包含n个用户的数据集提供了理论框架,其输出仅会泄露任意单个用户的极少信息。这类隐私概念通常通过加噪机制保障,并可通过子采样、混洗、迭代、混合及扩散等多种过程实现放大。在本研究中,我们给出了量子与量子启发式算法的隐私放大幅值边界。我们首次证明,运行于经典数据集的量子编码之上的算法,或是基于量子启发式经典采样结果的算法,均可放大幅分隐私。此外我们还证明,若量子信道满足特定混合条件,量子版本的差分隐私可通过量子信道的组合实现放大。

英文摘要:

Differential privacy provides a theoretical framework for processing a dataset about $n$ users, in a way that the output reveals a minimal information about any single user. Such notion of privacy is usually ensured by noise-adding mechanisms and amplified by several processes, including subsampling, shuffling, iteration, mixing and diffusion. In this work, we provide privacy amplification bounds for quantum and quantum-inspired algorithms. In particular, we show for the first time, that algorithms running on quantum encoding of a classical dataset or the outcomes of quantum-inspired classical sampling, amplify differential privacy. Moreover, we prove that a quantum version of differential privacy is amplified by the composition of quantum channels, provided that they satisfy some mixing conditions.

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。

↑