【InForSec@清华大学】机器学习和区块链中数据隐私的加密技术

时间:4月27日(周六)下午14:00-16:30

地点:清华大学FIT楼 3-225

演讲人:张宇鹏  加州大学伯克利分校博士后

报告题目:机器学习和区块链中数据隐私的加密技术 

主办单位:清华大学网络科学与网络空间研究院、InForSec

协办单位:北京信息科学与技术国家研究中心

演讲摘要

With the rapid development of rising techniques such as machine learning and blockchain, data privacy becomes a big concern. Companies are collecting more and more data from users so as to run machine-learning algorithms on that data to develop products and services. Users’ data are posted publicly on the blockchain for others to validate and reach consensus. Despite of the great benefits of these techniques, they currently require users to give up control of their data and to trade off integrity and privacy for utility. In this talk, I will discuss several cryptographic techniques I have developed to address these issues. I will first talk about privacy-preserving machine learning, which allows companies to execute machine-learning algorithms without learning users’ data. I will then discuss about techniques for verifiable computation and zero knowledge proof that can be used to ensure the correctness of computations without leaking information about the underlying data. 

随着机器学习和区块链技术的高速发展,数据隐私成为了一个重要问题。公司收集大量用户的数据去训练机器学习模型来应用到产品和服务中。在区块链应用中所有的数据都公开储存在区块链上使得所有用户得以验证并达成共识。虽然这些技术非常的成功,但现阶段他们需要用户牺牲数据的隐私来换取这些应用。本次讲座中会讨论一些我研究的基于密码学的技术来解决这些隐私问题。首先我会讲解通过多方计算加密的机器学习方法,使得公司可以在不得到用户数据内容的情况下训练机器学习模型。然后我会讨论可验证计算和零知识证明技术。他们可以在不泄漏数据的情况下用来证明数据和运算的正确性。

演讲人简介

Yupeng Zhang is an Assistant Professor in Computer Science and Engineering Department of Texas A&M University starting Fall 2019. He is currently a postdoctoral researcher at UC Berkeley working with Professor Dawn Song. His research is focused on applied cryptography, and his work on privacy-preserving machine learning, zero knowledge proof, verifiable computation and searchable encryption has been published at top security conferences. He is a recipient of Google PhD Fellowship and Distinguished Dissertation Award of ECE, University of Maryland. 

张宇鹏教授2019年秋季加入德州农工大学(TAMU塔木)计算机系开始助理教授职位,现在加州大学伯克利分校Dawn Song教授组进行博士后研究。他主要的研究方向是应用密码学和安全。他在多方安全计算的机器学习,零知识证明,可验证计算和可搜索加密方面有多篇论文发表在顶级安全会议上。他在博士期间获得谷歌博士奖学金和马里兰电子工程系最佳博士论文奖。

联系人:段海新, duanhx@tsinghua.edu.cn

清华大学网络科学与网络空间研究院

(注:本次无直播,欢迎来现场)

Bookmark the permalink.

Comments are closed.