Linfeng Ma — accepted AI-conference papers

2026

SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks

Xin Zhang, Zijin Yang, Kejiang Chen, Linfeng Ma, Weiming Zhang, Nenghai Yu

ICML 2026poster

Latent-based watermarks, integrated into the generation process of latent diffusion models (LDMs), simplify detection and attribution of generated images. However, recent black-box forgery attacks, where an attacker needs at least one watermarked image and black-box access to the provider’s model, c…

Cited by 1 Source ↗Scholar ↗

2024

A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability

Linfeng Ma, Han Fang*, Tianyi Wei, Zijin Yang, Zehua Ma*, Weiming Zhang +1

ECCV 2024oral

"Robustness is the most important property of watermarking schemes. In practice, the watermarking mechanism shall be robust to both geometric and non-geometric distortions. In deep learning-based watermarking frameworks, robustness can be ensured by end-to-end training with different noise layers. H…

Cited by 4 Source ↗PDF ↗Scholar ↗