Program
Schedule
(presentations will not be recorded/streamed)08:45 - 09:00 Welcome
09:00 - 09:45 Keynote
Rebecca Portnoff, Thorn
Safety by Design for Generative AI: Preventing Child Sexual Abuse
09:45 - 10:00 Break
10:00 - 10:45 Keynote
Justus Thies, Darmstadt University
Capturing & Controlling Digital Humans
10:45 - 11:45 Posters
11:45 - 01:30 Lunch
01:30 - 02:15 Keynote
Siwei Lyu, University at Buffalo
Rubber hits the Road: Lessons Learnt from DeepFake Detection in the Real World
02:15 - 03:15 Posters
03:15 - 03:45 Break
03:45 - 04:30 Keynote
John Collomosse, Adobe
To Authenticity, and Beyond! Building Safe and Fair Generative AI upon the Three Pillars of Provenance
04:30 - 05:00 Wrap up, discussion and future directions
AccEpted Papers
(papers will be published in CVPR proceedings)Finding AI-Generated Faces in the Wild
Gonzalo J Aniano Porcile (LinkedIn); Jack Gindi (LinkedIn); Shivansh Mundras (LinkedIn); James R Verbus (LinkedIn); Hany Farid (University of California, Berkeley)
An Investigation into the Impact of AI-Powered Image Enhancement on Forensic Facial Recognition
Justin D Norman (UC Berkeley); Hany Farid (University of California, Berkeley)
Lost in Translation: Lip-Sync Deepfake Detection from Audio-Video Mismatch
Matyas Bohacek (Stanford University); Hany Farid (University of California, Berkeley)
Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
Shan Jia (University at Buffalo ); Reilin Lyu (Williamsville East High School); Kangran Zhao (The Chinese University of Hong Kong, Shenzhen); Yize Chen (The Chinese University of Hong Kong, Shenzhen); Zhiyuan Yan (The Chinese University of Hong Kong, Shenzhen; Tencent Youtu Lab); Yan Ju (University at Buffalo); Chuanbo Hu (West Virginia University); Xin Li (SUNY Albany); Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen; Shenzhen Research Institute of Big Data); Siwei Lyu (University at Buffalo)
E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
Aref Azizpour (Drexel University); Tai D Nguyen (Drexel University); Manil Shrestha (Drexel University); Kaidi Xu (Drexel University); Edward Kim (Drexel University); Matthew C Stamm (Drexel University)
Fusion Transformer with Object Mask Guidance for Image Forgery Analysis
Dimitrios Karageorgiou (CERTH-ITI); Giorgos Kordopatis-Zilos (CTU in Prague); Symeon Papadopoulos (Information Technologies Institute / Centre for Research & Technology - Hellas, GR)
Raising the Bar of AI-generated Image Detection with CLIP
Davide Cozzolino (University Federico II of Naples); GIovanni Poggi (University Federico II of Naples); Riccardo Corvi (University Federico II of Naples); Matthias Niessner (Technical University of Munich); Luisa Verdoliva (University Federico II of Naples)
StampOne: Addressing Frequency Balance in Printer-proof Steganography
Farhad Shadmand (University of Coimbra); Iurii Medvedev (University of Coimbra); Luiz Schirmer (Unisinos); João S. Marcos (Instituto de Sistemas e Robótica - Universidade de Coimbra); Nuno Gonçalves (University of Coimbra)
Building Secure and Engaging Video Communication by Using Monitor Illumination
Jun Myeong Choi (University of North Carolina at Chapel Hill); Johnathan Leung (University of North Carolina at Chapel Hill); Noah Frahm (University of North Carolina at Chapel Hill); Max Christman (University of North Carolina at Chapel Hill); Gedas Bertasius (UNC Chapel Hill); Roni Sengupta (University of North Carolina at Chapel Hill)
Audio provenance analysis in heterogeneous media sets
Milica Gerhardt (Fraunhofer IDMT); Luca Cuccovillo (Fraunhofer IDMT); Patrick Aichroth (Fraunhofer IDMT)
Beyond Deepfake Images: Detecting AI-Generated Synthetic Videos
Danial Samadi Vahdati (Drexel University); Tai D Nguyen (Drexel University); Aref Azizpour (Drexel University); Matthew C Stamm (Drexel University)
Audio Transformer for Synthetic Speech Detection via Multi-Formant Analysis
Luca Cuccovillo (Fraunhofer IDMT); Milica Gerhardt (Fraunhofer IDMT); Patrick Aichroth (Fraunhofer IDMT)
FairSSD: Understanding Bias in Synthetic Speech Detectors
Amit Kumar Singh Yadav (Purdue University); Kratika Bhagtani (Purdue University); Davide Salvi (Politecnico di Milano); Paolo Bestagini (Politecnico di Milano); Edward Delp (Purdue University)
Beyond the Screen: Evaluating Deepfake Detectors under Moiré Pattern Effects
Razaib Tariq (Sungkyunkwan University (SKKU)); Minji Heo (SKKU); Shahroz Tariq (CSIRO's Data61); Simon S Woo (Sungkyunkwan University (SKKU)