Keynote Speakers
Workshop Program
Morning Session (9:00 – 10:30 AM)
9:00 – 9:05 — Opening Remarks
9:05 – 10:00 — Keynote A
10:00 – 10:30 — Paper Session 1: Attacks & Auditing
Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation
Yizhu Wen (University of Hawaii at Manoa), Shuhao Zhang (Clemson University), Nan Zhang (Michigan State University), Long Cheng (Clemson University), Hanqing Guo (University of Hawaiʻi at Mānoa)
Auditing Training Data in Generative Music Models via Black-Box Membership Inference
Yi Chen Liu (University of Georgia), Jiawei Yu (University of Georgia), Kexin Cao (Independent Researcher), Syed Irfan Ali Meerza (University of Tennessee, Knoxville), Trishika Movva (University of Georgia), Jian Liu (University of Georgia)
10:30 – 11:00 AM — Break
Morning Session (cont.) (11:00 AM – 12:00 PM)
11:00 – 11:55 — Keynote B
11:55 – 12:00 — Buffer
12:00 – 1:15 PM — Lunch
Afternoon Session (1:15 – 2:45 PM)
1:15 – 2:15 — Panel Discussion
Theme: TBD
2:15 – 2:45 — Paper Session 2: Watermarking & Robustness
FLEXMark: Evaluating Watermark Robustness and Attribution Reliability Under Redistribution and Adaptive AI Laundering
Natalia Ellen (National College of Ireland), Furqan Rustam (University College Dublin), Anca Delia Jurcut (University College Dublin)
RD-PHash: A Robustness Enhancement for DCT-Based Perceptual Hashing against Adversarial Bit-Flipping Attacks
Nan Jiang (National University of Singapore), Bangjie Sun (National University of Singapore), Nayoung Kim (KAIST), Terence Sim (National University of Singapore), Jun Han (KAIST)
2:45 – 3:15 PM — Break
Afternoon Session (cont.) (3:15 – 4:45 PM)
3:15 – 4:10 — Keynote C
4:10 – 4:25 — Paper Session 3: Vision & Generative Media
Artistic Camouflage: A Reversible Visual Cryptography Framework via Stable Diffusion
Yanyan Han (Beijing Electronic Science and Technology Institute), Suheng Wei (Beijing Electronic Science and Technology Institute), Kaili Dou (Beijing Electronic Science and Technology Institute)