PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection

arXiv:2605.09319 · cs.CV, cs.LG · Submitted 2026-05-10 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-05-10

Updated: 2026-10-13

Terminology

• Progressive Guided Inversion and Denoising — 2× in this paper
• Diffusion Model — 1× in this paper · explained in 9 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• SEAL: Semantic Aware Image Watermarking
• OSI: One-step Inversion Excels in Extracting Diffusion Watermarks
• Robust Invisible Video Watermarking with Attention
• Diffusion Models for Adversarial Purification
• WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
• Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
• T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
• SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
• Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image
• Pseudorandom Error-Correcting Codes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models