报告时间：2024年6月23日9:00-11:00

报告地点：增信园二号楼210会议室

报告题目：Bounded and Unbiased Composite Differential Privacy

Abstract:

The most kind of traditional DP (Differential Privacy) mechanisms (e.g. Laplace, Gaussian, etc.) have unlimited output range. In real scenarios, most datasets have their reasonable output range. Users have to utilize post-processing or truncated mechanisms to forcibly bind the output distribution in a specific range. However, these methods may introduce some biases, leading to issues of unfairness in subsequent applications due to these biases. This talk will first illustrate this bias challenge. Then, it will present a new DP mechanism named Bounded and Unbiased Composite Differential Privacy to address this challenge. It will detail the rational of this new scheme and example noise functions as well as their implementation algorithms.

Short Bio:

Dr Jinjun Chen is a Professor from Swinburne University of Technology, Australia. He holds a PhD in Information Technology from Swinburne University of Technology, Australia. His research interests include data privacy and security, cloud computing, scalable data processing, data systems and related various research topics. His research results have been published in more than 300 papers in international journals and conferences. He received various awards such as Editorial Excellence and Eminence Award of IEEE Transactions on Cloud Computing and IEEE TCSC Award for Excellence in Scalable Computing. He has served as an Associate Editor for various journals such as ACM Computing Surveys, IEEE TC, TCC and TSUSC. He is a MAE (Academia Europea) and IEEE Fellow (IEEE Computer Society). He is Chair for IEEE TCSC (Technical Community for Scalable Computing).