Program - AI4MFDD2026

8:50 – 9:00

Welcome

9:00 – 10:00

Keynote Speaker: Prof. Sebastiano Battiato
University of Catania, Italy

10:00 – 10:15

Break

10:15 – 11:00

Session 1 (Oral)

Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples
^{Roman Demchenko, Jonas Ricker, and Asja Fischer}

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
^{Gautier Evennou, Vivien Chappelier, and Ewa Kijak}

Non-Intrusive and Scalable Watermarking for Latent Diffusion Models via a Shared LoRA Adapter
^{Qiushi Li, Dongdong Lin, Shunquan Tan, Roberto Caldelli, and Stefano Berretti}

11:00 – 11:15

Break

11:15 – 12:00

Session 2 (Oral)

LSViT: Locality-Sensitive Vision Transformer Adaptation for Generalizable Deepfake Detection
^{Jinpeng Zheng, Wenbin Huo, Xindi Zhang, Yan Liang, Yanan Guo, and Jiani Hu}

Unifying Semantic Priors and High-Frequency Traces: Enhancing V-JEPA with Mixture-of-Experts for Robust Synthetic Image Forensics
^{Simone Teglia, and Irene Amerini}

Dissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection
^{Xianlong Li, Pietro Bongini, Niccolò Pancino, Marco Blanchini, Benedetta Tondi, and Mauro Barni}

12:00 – 13:30

Lunch Break

13:30 – 14:30

Keynote Speaker: Prof. Roberto Caldelli
Universitas Mercatorum (Rome) and
CNIT (Florence), Italy

14:30 –14:45

Break

14:45 – 15:45

Session 3 (IAPR-TC6 Best Paper Award)

DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization
^{Simon Freitter, David Fischinger, Silvia Poletti, Marcel Hasenbalg, and Martin Boyer}

DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection
^{Georgios Tsoumplekas, Vazgken Vanian, Alexandros Doumanoglou, Panos K. Papadopoulos, Yannis Spyridis, Dimitrios Zarpalas, and Vasileios Argyriou}

Understanding Why Foundation Models Work for Diffusion-Generated Image Detection
^{Davide Cozzolino, Giovanni Poggi, and Luisa Verdoliva}

Latent Optimization Dynamics for Latent Diffusion Model Attribution
^{Martin Dahlgren, and Abu Naser Masud}

15:45 – 16:00

Break

16:00 – 16:15

IAPR-TC6 Best Paper Award Announcement

16:15 – 18:30

Session 4 (Posters)

LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone Photos
^{Achim von Stryk and Janis Keuper}

Media Intelligence Platform: Multimodal Detection of Synthetic and Manipulated Content
^{David Fischinger, Marcel Hasenbalg, Silvia Poletti, Davide Antonutti, Mina Schütz, Lam Pham, Justin Ilyes, Péter Rjabcsenkó, Simon Freitter, and Martin Boyer}

Periocular Soft Biometrics: A Survey and Applications to Multimedia Forensics and Disinformation Detection
^{Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, and Josef Bigun}

A Cross-View Consistent Multi-Branch Framework for Synthetic Image Source Attribution
^{Nguyen Tu Nam, and Hiroki Takahashi}

AIGen4Det: Leveraging AI-Regeneration for Generalizable Synthetic Facial Image Detection
^{Andrea Ciamarra, Stefano Berretti, Alberto Del Bimbo, and Roberto Caldelli}

Don’t Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agent
^{Giulia Boato, Andrea Montibeller, Edward Delp, Luisa Verdoliva, and Daniele Miorandi}

Leveraging Speech-to-Facial-Electromyography Mapping for Singing Voice Deepfake Source Tracing: A Pilot Experiment
^{Oussama Jalleli, Yi Zhu, and Tiago Falk}