Papers for

content platform security teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Balancing watermark quality and robustness in diffusion image marking

Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies

Abstract: Watermarking diffusion-generated images requires balancing provenance signals with image quality, robustness, and computational cost. This work organizes methods along two axes: insertion mechanism and primary signal-bearing representation, and formalizes a representative $z_T$-Fourier pipeline for verification and identification. We then use the taxonomy to structure three protocol-bounded case studies. The first examines associations among frequency integrity, detection, quality, and cropping behavior. The second revisits persistence under seed-linked and seed-independent editing and formulates a scoped Semantic Imprinting Hypothesis without claiming a localized carrier or causal mechanism. The third studies single-shot VAE-latent phase modulation, including its efficiency, regeneration robustness, and robustness--quality operating points. Finally, we separate four content-level attack families from model/pipeline adaptation, propose corresponding evaluation protocols and testable conjectures for parameter-tuning threats, and identify additional temporal extensions for video. These analyses do not establish a universal ranking; instead, they provide a framework for matched, protocol-aware comparisons of watermarking systems for diffusion-generated images.

Wed 7 OctComputer Vision and Pattern Recognition
The gist
Watermarking images made by diffusion models is tricky because the marks must stay clear without ruining the picture. This paper sorts existing watermark methods by how they insert the marks and which part of the image stores the signal. The authors test different ways watermarks hold up to cropping, edits, and quality changes, and also propose ways to measure how well these marks survive attacks or changes. Their work provides a way to compare and evaluate watermarking methods fairly rather than saying which is the best.
Open → 2610.09755v1