BYR Achieve · 镜像论坛

学术报告：Reasoning about privacy: A technical perspective (从技术角度审视个人隐私) 应网络与交换技术国家重点实验室邀请，香港浸会大学计算机系研究助理教授陈睿将于11月19日来我校交流并作学术报告。欢迎有兴趣的师生踊跃参与。讲座题目：Reasoning about privacy: A technical perspective (从技术角度审视个人隐私)主讲人：Rui Chen (陈睿)主持人：苏森教授时间：2014年11月19日（周三）下午15：00地点：新科研楼510会议室 Abstract: With the increasing prevalence of various digital devices and computing services, we leave a large amount of digital traces in our daily lives. Such digital traces are valuable sources for diverse data analysis and data mining tasks. Yet, privacy threats in the course of data sharing have been a major impediment to the advancement of these tasks. In this talk, we will briefly review the technical efforts made by the data privacy community in the past fifteen years. Driven by various privacy attacks, privacy researchers have proposed a series of privacy models, such as k-anonymity, l-diversity and t-closeness, to define individual privacy from a technical perspective. Unfortunately, this line of privacy models is vulnerable to an attacker’s background knowledge. In recent years, differential privacy has emerged as the standard privacy notion that provides rigorous privacy guarantees independent of an attacker’s background knowledge. We will discuss the definition and basic properties of differential privacy, the challenges of applying differential privacy to social network data, and two preliminary solutions towards differentially private social network data publishing. 摘要：各种数码设备和计算服务的快速普及虽然为我们的生活带来了巨大便利，但也让我们在日常生活中留下了各种数字痕迹。这些数字信息一方面是数据分析和数据挖掘不可或缺的数据来源，另一方面也对个人隐私造成了严重威胁,进而阻碍数据挖掘的进一步发展。在这次讲座中，我们将简要回顾过去15年来数据隐私领域的发展。由于各种隐私攻击的不断出现，隐私研究者从技术的角度提出了一系列对应的隐私保护模型，比如k-anonymity、l-diversity和t-closeness。但由于攻击者背景知识的复杂性，它们均无法提供可靠的隐私保护。近年来，差分隐私成为了最广泛认可的隐私标准。它最大的特点是能够提供与背景知识无关的严格隐私保护。我们将讨论差分隐私的定义和基本性质，将差分隐私应用到社交网络数据的技术难点，并分享两个初步的解决方案。 Bio: Dr. Rui Chen is a Research Assistant Professor in the Department of Computer Science at Hong Kong Baptist University. He was a postdoctoral fellow at the University of British Columbia. He received his Ph.D. in Computer Science from Concordia University. During his Ph.D. studies, he worked as a research intern at INRIA, France. His research interests lie in databases and data mining, with a focus on data privacy. He has published over 20 papers in top journals and conferences, including ACM Computing Surveys, VLDBJ, PVLDB, JAMIA, SIGKDD, CCS and ICDM. He has served as program committee co-chair and member for ten international conferences and workshops. His research is funded by the Hong Kong General Research Fund. He is the recipient of Natural Sciences and Engineering Research Council of Canada (NSERC) Canada Graduate Scholarship, Fonds de recherche du Quebec - Nature et technologies (FRQNT) Postdoctoral Fellowship and Doctoral Research Scholarship. 个人简介：陈睿, 香港浸会大学计算机系研究助理教授，加拿大Concordia大学计算机博士。曾在英属哥伦比亚大学从事博士后研究工作，在法国国家信息与自动化研究院做研究实习。主要研究方向为数据库和数据挖掘，特别是数据隐私。先后在ACM Computing Surveys、VLDBJ、PVLDB、JAMIA、SIGKDD、CCS、ICDM等知名国际期刊和会议发表论文20多篇。曾担任10个国际会议的程序委员会主席或委员。主持香港政府研究基金资助的科研项目。曾获得加拿大国家自然科学基金委员会加拿大研究生奖学金，魁北克自然科学基金委员会博士后奖学金和博士研究奖学金。 http://portal.bupt.edu.cn//html/main/col38/2014-11/18/20141118141049377678894_1.html