Program

TBD

08:30 - 08:45 Welcome

08:45 - 09:30 Keynote: Shalini De Mello (Title: TBD)

09:30 - 09:45 Break

09:45 - 10:00 SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks

10:00 - 10:15 PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis

10:15 - 10:30 Phoneme-Level Analysis for Person-of-Interest Speech Deepfake Detection

10:30 - 10:45 Adversarial Reality for Evading Deepfake Image Detectors

10:45 - 11:15 Break

11:15 - 11:30 Is JPEG AI going to change image forensics?

11:30 - 11:45 FreqPure: a High-frequency Preservation Diffusion-based Purification Method for Protective Perturbation Removal

11:45 - 01:00 Lunch

01:00 - 01:15 Adaptive Test-Time Semantic Debiasing for AI-Generated Image Detection

01:15 - 01:30 CatAID: Category-Guided AI-Generated Image Detection via Vision-Language Model Adaptation

01:30 - 01:45 Explainable AI-Generated Image Forensics: A Low-Resolution Perspective with Novel Artifact Taxonomy

01:45 - 02:00 The Effect of Semantically Aligned Images for Deepfake Detection

02:00 - 02:30 Break

02:30 - 03:15 Keynote:  Sébastien Marcel (Title: From Face Recognition to Deception: 20 Years in Biometrics and Synthetic Media)

03:15 - 03:30 CustomMark: Customization of Diffusion Models for Proactive Attribution

03:30 - 03:45 MultiNeRF: Multiple Watermark Embedding for Neural Radiance Fields

03:45 - 04:00 Witness Sensing for Verifying the Human Origin of Digital Media

04:00 - 04:15 Break

04:15 - 05:30 Synthetic Video Detection Challenge Readout

• Challenge Overview

• Participant Presentations: 

  • ISPL (Politecnico di Milano) and Realynx – Sara Mandelli 

  • DASH Lab / Sungkyunkwan University – Sangyong Lee and Hyeongjun Choi 

  • DASH Lab / Sungkyunkwan University - Muhammad Shahid Muneer 

  • University of Naples Federico II – Davide Cozzolino 

  • Drexel University – Matt Stamm 

  • Truebees – Stefano Dell’anna  

  • Data eXperience Lab / Sungkyunkwan University - Hyeonbin Ji 

• Closing and Award Notification

SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks

Kutub Uddin, Awais khan, Muhammad Umar Farooq, Khalid Malik

CustomMark: Customization of Diffusion Models for Proactive Attribution

Vishal Asnani, John Collomosse, Xiaoming Liu, Shruti Agarwal

MultiNeRF: Multiple Watermark Embedding for Neural Radiance Fields

Yash Kulthe, Andrew Gilbert, John Collomosse

FreqPure: a High-frequency Preservation Diffusion-based Purification Method for Protective Perturbation Removal

Yan Ju, Hongfei Xue, Siwei Lyu

Adaptive Test-Time Semantic Debiasing for AI-Generated Image Detection

Yu Cai, Jiahe Tian, Xiaomeng Fu, Jiao Dai, Jizhong Han, Siwei Lyu

CatAID: Category-Guided AI-Generated Image Detection via Vision-Language Model Adaptation

Yu Cai, Shan Jia,Jiahe Tian, Jiao Dai, Jizhong Han, Siwei Lyu

Is JPEG AI going to change image forensics?

Edoardo Daniele Cannas, Sara Mandelli, Natasa Popovic, Ayman Alkhateeb, Alessandro Gnutti, Paolo Bestagini, Stefano Tubaro

Explainable AI-Generated Image Forensics: A Low-Resolution Perspective with Novel Artifact Taxonomy

Kaustubh Sharma

Phoneme-Level Analysis for Person-of-Interest Speech Deepfake Detection

Davide Salvi, Viola Negroni, Sara Mandelli, Paolo Bestagini, Stefano Tubaro

PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis

Soumyya Kanti Datta, Tanvi Ranga, Chengzhe Sun, Siwei Lyu

Adversarial Reality for Evading Deepfake Image Detectors

Umur A. Ciftci, Nicholas Solar, Emily Greene, Sophie Riley Saremsky, Ilke Demir

Witness Sensing for Verifying the Human Origin of Digital Media

Isabella Lenz, Yu Rong, Daniel Bliss, Julie Liss, and Visar Berisha

The Effect of Semantically Aligned Images for Deepfake Detection

Aritra Bandyopadhyay, Tyme Chatupanyachotikul, Jose L. Garcia, Arijit Ghosh, Karolina Hajkova, Carlos Miguel Patiño, Ivona Najdenkoska