KAIST Graduate School of Information Security

[세미나] Towards secure and privacy-preserving data collection for machine learning - 김형식 교수 (성균관대)
작성일2021-09-23
저희 정보보호대학원에서는 성균관대학교, 김형식 교수님을 모시고 "Towards secure and privacy-preserving data collection for machine learning" 주제로 아래와 같이 세미나를 개최하고자 합니다. ※ 코로나19 확산방지를 위하여 원격수업으로(ZOOM) 진행할 예정입니다. 참여를 원하시는 분들은 아래의 zoom의 참가기능을 이용하시면 됩니다. = 아 래 = o 일 시: 21.9.28(화) 16:00∼ ※ 세미나 시작시간 5분전에 준비하여 주세요. URL: https://zoom.us/j/2902905410 접속 비밀번호: 이메일 별도 공지 ================================== Title: Towards secure and privacy-preserving data collection for machine learning Abstract Recent advancements in deep learning techniques have greatly empowered various applications (e.g., object recognition, human activity recognition, health status monitoring, and environmental sensing). However, it has been shown that deep learning models face many privacy and security challenges such as adversarial samples, data poisoning, backdooring, and inference of sensitive training data. This talk first provides a brief overview of such privacy and security challenges and then presents several techniques towards enabling secure and privacy-preserving data collection for machine learning through some case studies on speech recognition, image processing, and collaborative learning. Bio Hyoungshick Kim is an associate professor in the Department of Computer Science and Engineering, College of Software, Sungkyunkwan University. He is also working as a distinguished visiting researcher at CSIRO Data61. He received a BS degree from the Department of Information Engineering at Sungkyunkwan University, an MS degree from the Department of Computer Science at KAIST, and a Ph.D. degree from the Computer Laboratory at the University of Cambridge in 1999, 2001, and 2012, respectively. After completing his Ph.D., he worked as a post-doctoral fellow in the Department of Electrical and Computer Engineering at the University of British Columbia. He previously worked for Samsung Electronics as a senior engineer from 2004 to 2008. He also served as a member of DLNA and Coral standardization for DRM interoperability in home networks. His current research interest is focused on usable security, blockchain, security vulnerability analysis, and data-driven security. ※ 카이스트 정보보호대학원 세미나는 카이스트 학생/교수, 그리고 Security＠KAIST 컨소시움 Silver 등급 이상의 회원사에 무료로 제공됩니다. 감사합니다.

[세미나] Towards secure and privacy-preserving data collection for machine learning - 김형식 교수 (성균관대)

작성일2021-09-23

저희 정보보호대학원에서는 성균관대학교, 김형식 교수님을 모시고 "Towards secure and privacy-preserving data collection for machine learning" 주제로 아래와 같이 세미나를 개최하고자 합니다.

※ 코로나19 확산방지를 위하여 원격수업으로(ZOOM) 진행할 예정입니다.
참여를 원하시는 분들은 아래의 zoom의 참가기능을 이용하시면 됩니다.

= 아 래 =

o 일 시: 21.9.28(화) 16:00∼
※ 세미나 시작시간 5분전에 준비하여 주세요.

URL: https://zoom.us/j/2902905410
접속 비밀번호: 이메일 별도 공지

==================================

Title: Towards secure and privacy-preserving data collection for machine learning

Abstract
Recent advancements in deep learning techniques have greatly empowered various applications (e.g., object recognition, human activity recognition, health status monitoring, and environmental sensing). However, it has been shown that deep learning models face many privacy and security challenges such as adversarial samples, data poisoning, backdooring, and inference of sensitive training data. This talk first provides a brief overview of such privacy and security challenges and then presents several techniques towards enabling secure and privacy-preserving data collection for machine learning through some case studies on speech recognition, image processing, and collaborative learning.

Bio
Hyoungshick Kim is an associate professor in the Department of Computer Science and Engineering, College of Software, Sungkyunkwan University. He is also working as a distinguished visiting researcher at CSIRO Data61. He received a BS degree from the Department of Information Engineering at Sungkyunkwan University, an MS degree from the Department of Computer Science at KAIST, and a Ph.D. degree from the Computer Laboratory at the University of Cambridge in 1999, 2001, and 2012, respectively. After completing his Ph.D., he worked as a post-doctoral fellow in the Department of Electrical and Computer Engineering at the University of British Columbia. He previously worked for Samsung Electronics as a senior engineer from 2004 to 2008. He also served as a member of DLNA and Coral standardization for DRM interoperability in home networks. His current research interest is focused on usable security, blockchain, security vulnerability analysis, and data-driven security.

※ 카이스트 정보보호대학원 세미나는 카이스트 학생/교수, 그리고 Security＠KAIST 컨소시움 Silver 등급 이상의 회원사에 무료로 제공됩니다.

감사합니다.

목록으로