4 papers
DHMark: Public-Key Watermarking for LLM-Generated Text via Diffie-Hellman-Guided Rejection Sampling
Haocheng Fu, Yuqi Qian, Luyao Wang +1
Large language model (LLM) watermarking provides an important mechanism for tracing the provenance of generated text. Existing statistical watermarks are often effective and robust…
AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony
Yuqi Qian, Yun Cao, Haocheng Fu +3
Inversion-based watermarking embeds watermark payloads directly into the generative process, avoiding a separate post-hoc image-domain embedding stage while preserving the native v…
ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
Yuqi Qian, Yun Cao, Haocheng Fu +2
Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introd…
CIF: A Constrained Inversion Framework for Reliable Message Extraction in Diffusion-Based Generative Steganography
Yuqi Qian, Yun Cao, Meiyang Lv +1
Generative image steganography aims to conceal secret information in generated images without arousing suspicion. However, in practical scenarios involving high-capacity embedding…