Latent Watermarks under Generative Editing: A Benchmark and Analysis of Detection Survival

arXiv:2610.09702 · cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/black-forest-labs/flux

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• WAVES: Benchmarking the Robustness of Image Watermarks
• Variational image compression with a scale hyperprior
• Prompt-to-Prompt Image Editing with Cross Attention Control
• Understanding Semantic Perturbations on In-Processing Generative Image Watermarks
• DINOv2: Learning Robust Visual Features without Supervision
• JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
• Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing

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