"post-hoc watermarking" Papers
2 papers found
SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
Zhuohao Yu, Xingru Jiang, Weizheng Gu et al.
NEURIPS 2025posterarXiv:2508.08211
1
citations
Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
Tomas Soucek, Sylvestre-Alvise Rebuffi, Pierre Fernandez et al.
NEURIPS 2025spotlightarXiv:2510.20468