Talk: State-of-the-art Approaches in Reducing GenAI Dis/misinformation

Posted on by

Generative AI has enabled the production of misinformation and disinformation on an unprecedented scale. As advertised by the VU, Profesor Wael AbdAlmageed will present the latest methods his group are creating to prevent these threats to child safety, public opinion, democracy and criminal justice. The talk is called: “Truth Decay-Plausible Deniability: The Liar’s Dividend”.

  • When: May 2nd (2024), 11:00-12:00
  • Where: VU Amsterdam, NU-4A25 and online 
    • No registration needed- just turn up!

Agenda

  1. Brief overview of current challenges in multimedia forensics
  2. Presentation of two novel multimedia forensics methods developed by Prof. Wael AbdAlmageed’s group:
    1. State-of-the-art approach to fingerprinting and attributing AI-generated images based on constructing representation manifolds from image embeddings.
    2. State-of-the-art deepfake detection architecture using intra- and inter-modal self-consistency.
  3. Wrap up with conclusions and thoughts for future directions in multimedia forensics research and ethical artificial intelligence in general

Dr. Wael AbdAlmageed

About Dr. Wael AbdAlmageed

Dr. Wael AbdAlmageed is a Tenured Full Professor with the Holcombe Department of Electrical and Computer Engineering at Clemson University. Until 2024, he was a Research Associate Professor at the Department of Electrical and Computer Engineering and the Computer Science Department, and a Research Director and Distinguished Principal Scientist with the Information Sciences Institute, all are units of USC Viterbi School of Engineering. He is the Founding Director of the Visual Intelligence and Multimedia Analytics Laboratory (VIMAL). He obtained his B.S. in electrical engineering in 1994 and his M.S. in computer engineering in 1997 from Mansoura University in Egypt. He also obtained a graduate software engineering diploma in 1997 from the Information Technology Institute in Egypt via a scholarship granted to distinguished graduates from Egyptian universities. He earned his Ph.D. with Distinction from the University of New Mexico in 2003 where he was also awarded the Outstanding Graduate Student award. Prior to joining ISI, Dr. AbdAlmageed was a research scientist with the University of Maryland at College Park, where he led several research efforts for various NSF, DARPA and IARPA programs. His research interests include representation learning, debiased and fair artificial intelligence, and application of artificial intelligence to medicine and healthcare. Dr. AbdAlmageed leads several multi-institution research efforts, including DARPA’s MediFor, GARD and LwLL and IARPA’s Janus, Odin and BRIAR. He has over 1000 publications in top computer vision, machine learning and biometrics conferences and journals, including CVPR, NeurIPS, ICCV, ECCV, ACM MM, PAMI, TBIOM and ICB. Dr. AbdAlmageed is the recipient of 2019 and 2022 USC Information Sciences Institute Achievement Award. His research has also been featured in CNN, Forbes, Glamour UK, Fox News, Time For Kids and PCMag.

Thanks to Filip Ilievski for sharing this with us.