페이지 정보작성자 최고관리자 작성일 22-04-28 12:01
장소 : https://yonsei.zoom.us/j/98392907869
ID 및 PW : 983 9290 7869
세미나 제목: Current Status, Challenges, and Possible Solutions for Deepfake Detection
세미나 초록: Deepfakes have become a critical social problem, and detecting them is of utmost importance. Detecting high-quality deepfake videos from widely released datasets are more straightforward to detect than low-quality ones. Most of the prior research achieve above 90% accuracy for detecting the high-quality deepfake videos from the open dataset. However, in real life, many deepfake videos that are leaked through social networks such as YouTube and instant messaging applications are highly compressed. As a result, the distributed video's resolution becomes extremely lower, making highly accurate detection methods becomes harder. In this work, we present the current status, several challenges, and possible solutions
- Bio: Currently, Simon Woo (http://dash.skku.edu) is a tenure-track Assistant Professor in CS/AI/Data Science depts at Sungkyunkwan University (SKKU). He received his Ph.D. from the University of Southern California, Los Angeles/Information Sciences Institute (USC/ISI). His current research focuses on AI security as well as anomaly detection for time series and vision applications. In particular, he aims to develop a wide range of data-driven AI methods to improve the detection of deepfakes. Also, his other research interest is on data and machine learning privacy to improve the robustness of the-state-of-the-art machine leaning algorithms, and address privacy issues in the end-to-end machine learning pipeline. In addition, he works on satellite operations, SAR image detection and object detection, etc. He is the organizer for the first Workshop on the Security Implications of Deepfakes and Cheapfakes (WDC) at AsiaCCS 2022.
Before joining SKKU, he was a Member of Technical Staff for 9 years at the NASA’s Jet Propulsion Laboratory (JPL), Pasadena, CA, conducting research in satellite communications, computer networking, AI, and security. Also, he worked at Intel Corp, and Verisign Research Labs. He earned his B.S. in Electrical Engineering degree (B.S.EE) from Univ. of Washington (UW), Seattle, M.S. in Electrical and Computer Engineering degree (M.S.ECE) from Univ. of California, San Diego (UCSD), and M.S. (M.S.CS) and Ph.D. in Computer Science from USC.
등록된 댓글이 없습니다.