Tencent Conference ID:534-173-095; Code:1309
Jie Ding Assistant Professor University of Minnesota
The emerging public awareness and government regulations of data privacy motivate new paradigms of collecting and analyzing data transparent and acceptable to data owners. This talk will introduce a new concept of privacy and related data formats, mechanisms, and theories for statistically privatizing data during data collection. The new privacy mechanisms will record each data value as a random interval (or, more generally, a range) containing it. Such mechanisms can be easily deployed through survey-based data collection interfaces, e.g., by asking a respondent whether its data value is within a randomly generated range. Using narrowed range to convey information is complementary to the popular paradigm of perturbing data. Also, the proposed mechanisms can generate progressively refined information at the discretion of individuals, naturally leading to privacy-adaptive data collection. This talk will demonstrate unique perspectives brought by Interval Privacy for human-centric data privacy, where individuals enjoy a perceptible, transparent, and simple way of sharing sensitive data.
Brief introduction of the speaker:
Jie Ding (http://jding.org/) is an Assistant Professor at the School of Statistics, University of Minnesota. Jie's research focus is on the foundations of machine learning, statistics, and signal processing, with recent interests in data privacy, machine learning security, and decentralized learning. Before joining the University of Minnesota in 2018, he received a Ph.D. in Engineering Sciences in 2017 from Harvard University and worked as a post-doctoral fellow at Duke University. Before that, Jie graduated from Tsinghua University in 2012, enrolled in Math & Physics training program and the Electrical Engineering program.