May
19
Date: 19-May-2026
Time: 11:00 AM ET (New York Time)
Duration: Approximately 60 minutes
Presenter: Dr. Luisa Verdoliva
Moderator: Dr. Siwei Lyu
Abstract
With the rapid progress of generative AI in recent years, techniques for generating and manipulating multimedia content have reached a very advanced level of realism. Powered by large language models, synthesis tools allow users to modify or create images and videos from scratch using simple text instructions. This talk will discuss the strengths and weaknesses of current deepfake detectors, especially in real-world scenarios, and present some possible strategies to overcome them.
Biography
Luisa Verdoliva (M’11-F’21) received the Laurea degree in telecommunications engineering and the Ph.D. degree in information engineering from the University of Naples Federico II, Naples, Italy, in 1998 and 2002, respectively.
She is currently a Professor with the Department of Electric Engineering and Information Technology at the University of Naples Federico II, Naples, Italy, where she leads the Multimedia Forensics Lab. She has also served (2020-2024) as a Hans Fischer Senior Fellow with the Institute for Advanced Study at the Technical University of Munich, Munich, Germany. Previously, she was a Visiting Scientist with Google AI in San Francisco, CA, USA, and a Visiting Professor with the Friedrich-Alexander-University, Erlangen, Germany. She has published over 150 academic papers, including: “Media Forensics and DeepFakes: an overview,” IEEE Journal of Selected Topics in Signal Processing, 2020; “Noiseprint: A CNN-based camera model fingerprint,” IEEE Transactions on Information Forensics and Security, 2020; and “FaceForensics++: Learning to Detect Manipulated Facial Images,” International Conference on Computer Vision, 2019. Her current and previous research interests include multimedia forensics, deepfake detection, and image and video forgery detection and localization.
Dr. Verdoliva is a member of the European Association for Signal Processing (EURASIP). Her awards include the NVIDIA Research Faculty Fellow (2026), the IEEE Signal Processing Society Best Paper Award (2025), the Frontiers of Science Award (2025) and the Google Faculty Research Award (2018). She served as the Chair of the IEEE Signal Processing Society's Information Forensics and Security Technical Committee from 2021 to 2022 and currently serves as the Editor-in-Chief for IEEE Transactions on Information Forensics and Security.
Siwei Lyu (M’06–F’22) received the B.S. degree in information science and the M.S. degree in computer science from Peking University, Beijing, China, and the Ph.D. degree in computer science from Dartmouth College, Hanover, NH, USA, in 1997 and 2000 & 2005 respectively.
He is currently a SUNY Empire Innovation Professor with the Department of Computer Science and Engineering, the Director of the UB Media Forensic Lab (UB MDFL), and the founding Co-Director of the Center for Information Integrity (CII) at the University at Buffalo, State University of New York, Buffalo, NY, USA. Previously, he served as a Professor at the University at Albany, State University of New York, and was a Post-Doctoral Research Associate with the Howard Hughes Medical Institute and the Center for Neural Science at New York University. His current and previous research interests include digital media forensics, computer vision, and machine learning.
Dr. Lyu is a Fellow of the International Association for Pattern Recognition (IAPR) and the Asia-Pacific Artificial Intelligence Association (AAIA). He is also a Distinguished Member of the Association for Computing Machinery (ACM), a Senior Member of the Sigma Xi Society, and a Member of the Omicron Delta Kappa Society. His most recent awards include the IEEE Region 1 Technological Innovation (Academic) Award (2021), the Google Faculty Research Award (2019), and the SUNY Chancellor’s Award for Excellence in Research and Creative Activities (2018). He has published over 190 refereed journal and conference papers.
