Recent Advances and Challenges of Deepfake Detection
About this Topic:
Currently, the rapid advancement of generative artificial intelligence, particularly diffusion models and large language models, has enabled the creation or manipulation of high-quality multimedia. Although beneficial in numerous fields, AI generated content presents significant risks, including potential misuse and ethical concerns. Consequently, detecting the generated multimedia has become increasingly popular in related research. This webinar presents a comprehensive overview of recent deep learning-based approaches for AI generated content detection. Our presenter also introduces their Masked Relation Learning method that formulates detection as a graph classification problem, and test-time detection method with spatial-frequency prompt learning. Furthermore, he will identify current challenges in detection and propose directions for future research.
About the Presenter:
Ran He (F’25) received the Ph.D. degree in pattern recognition and intelligent systems from the Institute of Automation, Chinese Academy of Sciences (CASIA), China, in 2009.
He is currently a professor at the National Laboratory of Pattern Recognition since December 2016 and is now directing the visual perception and machine learning group.
Dr. He has published two books and more than 200 papers in refereed journals and conference proceedings in the areas of computer vision, pattern recognition and image processing. He is a Fellow of IEEE and also a Fellow of IAPR and is the editor board member of IEEE TPAMI, TIP, TIFS, TCSVT, TBIOM and IJCV and was the area chair of ICCV, CVPR, ECCV, ICML, ICLR, NeurIPS. His awards and honors include IEEE SPS Young Author Best Paper Award, IAPR ICPR Best Scientific Paper Award, IEEE ICB Honorable Mention Paper Award, CAS Outstanding Tutor Award, IEEE SPS Outstanding Editorial Board Member Award, and Pattern Recognition best associate editor award.
Want to learn more about upcoming events & webinars?
Visit the events section of the Signal Processing website to see all upcoming lectures, workshops, webinars, and more.