CS Colloquium - Siwei Lyu, SUNY Albany
Title: Seeing is Deceiving: The rise of fake media & how we can fight back with technologies
Host: Marynel Vazquez
The past few years have seen a startling and troubling rise in fake online media that are challenging visual imagery as a definite record of reality. In particular, recent and rapid advances in machine learning are making it easier than ever to create sophisticated and compelling fake images and videos, escalating the scale and danger of the fake-news phenomena. In this talk, I will first briefly review the evolution of techniques behind the generation of fake media, and then introduce several projects I was involved in digital media forensics for detection of fake media, with a special focus on some of our recent works on detecting AI-generated fake videos (DeepFakes). This talk should be accessible to CS undergraduate students.
Siwei Lyu received his BS degree in Information Science from Peking University, China, in 1997, and his MS degree in Computer Science and Technology from Peking University, China, in 2000. He received his PhD degree in Computer Science from Dartmouth College, Hanover, New Hampshire, USA in 2005. From 2005 to 2008, he was a Post-Doctoral Research Associate at the Howard Hughes Medical Institute and the Center for Neural Science of New York University. Starting in 2008, he holds the position of Assistant Professor at the Computer Science Department of University at Albany, State University of New York, Albany, New York, USA. He was promoted to Associate Professor with tenure in 2014. His scientific research interests include machine learning, computer vision and digital media forensics. Dr. Lyu is the recipient of IEEE Signal Processing Society Best Paper Award in 2010, the National Science Foundation Early Faculty CAREER Award in 2011, University at Albany’s Presidential Award for Excellence in Research and Creative Activities in 2017, SUNY Chancellor’s Award for Excellence in Scholarship and Creative Activities in 2018. His research projects are funded by NSF, DARPA, ARO, and NIJ, totaling more than $3.5 million. He has authored and contributed to two books on digital image forensics, and held three US and one EU and one Japan patents. He has more than 100 scientific publications, many published in top conference (including ICML, NIPS, CVPR, ICCV, ECCV, UAI, IJCAI, AAAI and ECML) and journals (including PNAS, IEEE TPAMI, IJCV, IEEE TIP, IEEE TIFS and PR) in the research fields of machine learning and computer vision. His work in digital media forensics has been featured in national and international media including The Economist, Washington Post, New York Times, The Wired Magazine, Science Friday (radio interview) and Spectrum News (TV interview). Dr. Lyu serves on the IEEE SPS Information Forensics and Security Technical Committee (2017-2019), and is on the Editorial Board of IEEE Transactions on Information Forensics and Security. He is a senior member of IEEE since 2016, and is a member of the prestigious Omicron Delta Kappa (OΔK) Society since 2018.