Program
Monday, 08 September 2025, 09:20 AM – 11:20 AM
Learning the Difference with TimFusNet: A Deep Time-Frequency Encoding Approach for Generalizable Face Morphing Detection; Manasa R, Raghavendra Ramachandra, Pavan Kumar, Sushma Venkatsh
User-Customizable Voice Anonymization Through Personalized Style Transfer; Wenny Ramadha Putri, Chun-Shien Lu, Jia-Ching Wang
SFCL: A Spatial-Frequency Collaborative Learning Framework for Generalizable Deepfake Detection; Mengyu Qiao, Runze Tian, Yunpeng Zhai, Chen Li
Investigating the Viability of employing Multi-modal Large Language Models in the context of Audio Deepfake Detection; Akansha R, Shuesh Reddy, Sudeepta R, Abhijit Das, Abhinav Dhall
A Controllable 3D Deepfake Generation Framework with Gaussian Splatting; Wending Liu, Siyun Liang, Huy Nguyen, Isao Echizen
Each paper presentation will be given 15 minutes, followed by 5 minutes for Q&A.
Please note that each accepted paper must have at least one registered author.
All presentations must be delivered in person. Virtual presentations are not permitted. If a paper is not presented in person, it will be excluded from the proceedings.