arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09587cs.CR
收藏

差分隐私的开源工具评估

Evaluation of Open-source Tools for Differential Privacy

Shiliang Zhang, Anton Hagermalm, Sanjin Slavnic, Elad Michael Schiller, Magnus Almgren

摘要:

差分隐私(DP)通过承诺同意共享其隐私敏感信息的个体与不同意共享其隐私的个体之间的量化不可否认性来定义隐私保护。DP旨在通过在发布的数据中包含精心制作的随机噪声元素来实现这一承诺,因此在隐私保护程度和利用受保护数据的能力之间存在固有的权衡。目前,提出了几个开放源码工具来提供DP。据我们所知,目前还没有全面的研究来比较这些开源工具在平衡DP固有权衡以及系统资源使用方面的能力。这项工作为隐私保护解决方案提出了一个开源评估框架,并为OpenDP Smartnoise,Google DP,PyTorch Opacus,Tensorflow Privacy和Diffprivlib提供了评估。除了研究它们平衡上述权衡的能力之外,我们还考虑了离散和连续属性,通过量化它们在不同数据大小下的性能。我们的研究结果揭示了几种模式,开发人员在选择不同的应用程序的需求和标准的工具时,应该记住。这一评价调查可以作为改进开放源码发展伙伴关系工具选择和更快适应发展伙伴关系的基础。

英文摘要:

Differential privacy (DP) defines privacy protection by promising quantified indistinguishability between individuals that consent to share their privacy-sensitive information and the ones that do not. DP aims to deliver this promise by including well-crafted elements of random noise in the published data and thus there is an inherent trade-off between the degree of privacy protection and the ability to utilize the protected data. Currently, several open-source tools were proposed for DP provision. To the best of our knowledge, there is no comprehensive study for comparing these open-source tools with respect to their ability to balance DP's inherent trade-off as well as the use of system resources. This work proposes an open-source evaluation framework for privacy protection solutions and offers evaluation for OpenDP Smartnoise, Google DP, PyTorch Opacus, Tensorflow Privacy, and Diffprivlib. In addition to studying their ability to balance the above trade-off, we consider discrete and continuous attributes by quantifying their performance under different data sizes. Our results reveal several patterns that developers should have in mind when selecting tools under different application needs and criteria. This evaluation survey can be the basis for an improved selection of open-source DP tools and quicker adaptation of DP.

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。

↑