计算机软件新技术国家重点实验室   

摘 要：

Secure multi-party computation refers to the ability of multiple participants to jointly evaluate a function of their choice on their respective private data without disclosing any unintended information about it. This field of research has experienced notable advances in recent years, in terms of both the speed these techniques provide and the availability of tools and compilers that aid programmers in synthesizing secure distributed implementations for their desired functionality. Most recently, there has been a lot of interest in scalable privacy-preserving machine learning, where we desire to train a machine learning model on private data distributed across multiple sites or evaluate a private model on a private input without disclosing private data. As part of this talk, we will touch on the recent progress in secure computation and then look at operations of interest for privacy-preserving machine learning. We will discuss optimizations to the state of the art in the secret sharing setting on the example of reading an element at a private location.

报告人简介:

Marina Blanton is an Associate Professor in the Department of Computer Science and Engineering at the University at Buffalo. She received her MS in EECS from Ohio University in 2002, MS in CS from Purdue University in 2004, and PhD in CS from Purdue University in 2007. Dr. Blanton's research interests are centrally in information security, privacy, and applied cryptography. Recent projects span areas such as secure computation and outsourcing, integrity of outsourced computation and storage, and private biometric and genomic computation. Dr. Blanton has 70 refereed publications and has served on technical program committees of top conferences such as ACM CCS and IEEE S&P and is currently an associate editor of IEEE Transactions on Information Forensics and Security. She received multiple awards for her research including a 2013 AFOSR Young Investigator Award, the 2015 ACM CCS Test of Time Award, and a 2018 Google Faculty Research Award.

时间:12月8日(星期日）10:30-11:30

地点:鼓楼校区计算中心楼303会议室