08:00 – 09:00
08:00 – 09:00
Embedded Files
Registration, Coffee, Networking
Registration, Coffee, Networking
Workshop Session # 1
Workshop Session # 1
09:00 – 09:10
09:00 – 09:10
Welcome by Prof. Simon S. Woo
3D-Sec Co-Chair
Welcome by Prof. Simon S. Woo
3D-Sec Co-Chair
09:10 – 10:10
09:10 – 10:10
Keynote I
Keynote I
45 mins + 5 mins (Q/A)
45 mins + 5 mins (Q/A)
Title: Gauging Deepfake Detection for Real World Uses
Speaker: Professor Siwei Lyu (University of Buffalo - SUNY, USA)
Speaker’s Bio
Speaker’s Bio
Siwei Lyu is a SUNY Distinguished Professor and a SUNY Empire Innovation Professor at 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, USA. Dr. Lyu's research interests include media forensics, computer vision, and machine learning. He has published over 240 refereed journal and conference papers. He is a Fellow of IEEE, IAPR, and a Distinguished Member of ACM.
Abstract
Abstract
The rapid evolution of generative AI has brought unprecedented challenges to the integrity of social media information ecosystem. While detection methods have achieved notable success on benchmarking datasets, our experience shows that they often struggle in real-world scenarios suffering significant performance drops and mistrust from the practitioners. We analyze the root causes of these issues and overview our recent work to alleviate them.
Invited Papers
Invited Papers
15 mins + 5 mins (Q/A)
15 mins + 5 mins (Q/A)
10:10 – 10:30
10:10 – 10:30
Tamper-evident Image using JPEG Fixed Points
Zhaofeng Si, Siwei Lyu (buffalo.edu)
10:30 – 11:00
10:30 – 11:00
Coffee Break
Coffee Break
Workshop Session # 2
Workshop Session # 2
Paper Presentations
Paper Presentations
Each Paper: 15 mins + 5 mins (Q/A)
Each Paper: 15 mins + 5 mins (Q/A)
11:00 – 11:20
11:00 – 11:20
Exaggeration-based Fake Cybersecurity News Detection
Abdullah Felemban (The Ohio State University); Mustafa Ghaleb, Muhamad Felemban (King Fahd University of Petroleum and Minerals)
11:20 – 11:40
11:20 – 11:40
CLaRE: CLIP with Latent Reconstruction Errors for Generated Face Detection
Udit Thakur, Mohammad Hafeez Khan, Meher Changlani, Asen Dotsinski, Aswin Krishna Mahadevan, Ioannis Kechagias (University of Amsterdam); Ivona Najdenkoska (University of Amsterdam, Netherlands Forensic Institute (NFI))
11:40 – 12:00
11:40 – 12:00
Improved Estimation of Check-Worthy Social Media Content Using the Analysis of Commentaries
Raphael Antonius Frick, Taejeong Kwon (Fraunhofer SIT | ATHENE Center)
12:00 – 13:30
12:00 – 13:30
Lunch Break
Lunch Break
Workshop Session # 3
Workshop Session # 3
13:30 – 14:20
13:30 – 14:20
Keynote 2
Keynote 2
45 mins + 5 mins (Q/A)
45 mins + 5 mins (Q/A)
Title: Title: Synthetic Media Verification in the Era of Generative AI
Speaker: Professor Luisa Verdoliva (University Federico II of Naples, Italy)
Speaker’s Bio
Speaker’s Bio
Luisa Verdoliva is a Professor at University Federico II of Naples, Italy, where she leads the Multimedia Forensics Lab. Her scientific interests are in the field of image and video processing, with main contributions in the area of multimedia forensics. She has actively contributed to the academic community through service as General Chair of WACV 2024, Workshop Chair of CVPR 2024 and Technical Chair of IJCB 2023, IH&MMsec 2021, WIFS 2019. She is a former Chair of the IFS-TC for the 2021-2022 term and is Editor-in-Chief of the IEEE Transactions on Information Forensics (2025-2027). She is the recipient of the 2025 Frontiers of Science Awards, 2018 Google Faculty Research Award and a TUM-IAS Hans Fischer Senior Fellowship (2020-2024). She is an IEEE Fellow.
Abstract
Abstract
With the rapid progress of recent years, techniques that generate and manipulate multimedia content can now provide a very advanced level of realism. Powered by large language models, text-driven synthesis tools allow the user to modify or create from scratch images and videos by means of simple text instructions. On the one hand, this opens the door to a series of exciting applications in different fields such as creative arts, advertising, film production, video games. On the other hand, it poses enormous security threats. Therefore, there is an urgent need for automated tools capable of detecting false multimedia content and avoiding the spread of dangerous false information. This talk aims to present an analysis of the methods for synthetic media verification. Special emphasis will be placed on the phenomenon of AI-generated content and on modern data-driven forensic methods to fight them. The analysis will help highlight the limits of current forensic tools, the most relevant issues, the upcoming challenges, and suggest future directions for research.
Paper Presentations
Paper Presentations
Each Paper: 15 mins + 5 mins (Q/A)
Each Paper: 15 mins + 5 mins (Q/A)
14:20 – 14:40
14:20 – 14:40
Leveraging 3D Gaussian Splatting for Real-Time Facial Expression Transfer
Raphael Antonius Frick, Erik Gelbing, Lukas Graner (Fraunhofer SIT | ATHENE Center)
14:40 – 15:00
14:40 – 15:00
Few-Shot Detection of Hate Videos Using Multi-Modal Large Language Models
Jin Ma, Mohammed Aldeen, Feng Luo, Long Cheng (Clemson University)
15:00 – 15:30
15:00 – 15:30
Coffee Break
Coffee Break
Workshop Session # 4
Workshop Session # 4
Paper Presentations
Paper Presentations
Each Paper: 15 mins + 5 mins (Q/A)
Each Paper: 15 mins + 5 mins (Q/A)
15:30 – 15:50
15:30 – 15:50
Seeing is No Longer Believing: How Deepfakes May Shape the Future of Identity Credibility in Media
Raphael Antonius Frick, Niklas Bunzel, Lukas Graner (Fraunhofer SIT | ATHENE Center)
15:50 – 16:10
15:50 – 16:10
Scalable and Accurate Deepfake Detection
Alka Luqman, Anupam Chattopadhyay (Nanyang Technological University); Mondal Soumik (Institute for Infocomm Research (I2R), A*STAR, Singapore); PURUSHOTTAM DEWANGAN, Sagar Pingale (Deepfaic)
16:10 – 16:30
16:10 – 16:30
Defending Speaker Verification Against Deepfake: A Multi-Step Approach
Thien-Phuc Doan, Hung Dinh-Xuan, Inho Kim, Woongjae Lee, SeongKyu Han, Souhwan Jung (Soongsil University)
16:30 – 17:00
16:30 – 17:00
Closing Remarks
Closing Remarks
Page updated
Google Sites
Report abuse