【专家简介】：孔令龙博士是阿尔伯塔大学数学与统计科学系的教授。他拥有加拿大统计学习研究主席、加拿大CIFAR人工智能主席以及阿尔伯塔省机器智能研究所（AMII）研究员。他的出版记录包括在AOS、JASA和JRSSB等顶级期刊以及NeurIPS、ICML、ICMM、AAAI和IJCAI等顶级会议上发表的80多篇同行评审文章。孔博士目前担任《美国统计协会杂志》、《加拿大统计杂志》和《统计及其接口》的副主编，以及《统计及其界面》的客座编辑。此外，孔博士还是国际生物识别学会北美西部地区执行委员会成员、ASA统计计算会议项目主席和网络研讨会委员会主席。他曾担任《加拿大统计杂志》客座编辑、《国际成像系统与技术杂志》副编辑、《神经科学前沿》客座副编辑、ASA统计成像会议主席以及加拿大统计学会董事会成员。他对高维和神经成像数据的分析、统计机器学习、稳健统计和分位数回归以及用于智能健康的人工智能感兴趣。
【报告摘要】：Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of sensitive individual information. Despite the extra interpretability and tighter bounds under composition GDP provides, many widely used mechanisms (eg, the Laplace mechanism) inherently provide GDP guarantees but often fail to take advantage of this new framework because their privacy guarantees were derived under a different background. In this paper, we study the asymptotic properties of privacy profiles and develop a simple criterion to identify algorithms with GDP properties. We propose an efficient method for GDP algorithms to narrow down possible values of an optimal privacy measurement, $\mu$ with an arbitrarily small and quantifiable margin of error. For non GDP algorithms, we provide a post-processing procedure that can amplify existing privacy guarantees to meet the GDP condition. As applications, we compare two single-parameter families of privacy notions, $\epsilon$-DP, and $\mu$-GDP, and show that all $\epsilon$-DP algorithms are intrinsically also GDP. Lastly, we show that the combination of our measurement process and the composition theorem of GDP is a powerful and convenient tool to handle compositions compared to the traditional standard and advanced composition theorems.
时 间：2023年7月4日 9:00
地 点：位育楼417+线上（腾讯会议号392612556）
