AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification

Hai Ci, Pei Yang, Yiren Song, Mike Zheng Shou

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use RingID instead of Tree-Ring for verificationStable Diffusion v2 watermarking · Verification, average AUCROC-AUC: 0.975 -> 0.995Improved
use RingID instead of Tree-Ring for 32-key identification (excluding C&S)Stable Diffusion v2 watermarking · Identification, 32 keysidentification accuracy: 0.465 -> 0.992Improved
use RingID instead of Tree-Ring for 2048-key identification (excluding C&S)Stable Diffusion v2 watermarking · Identification, 2048 keysidentification accuracy: 0.077 -> 0.942Improved
add discretization of ring values to plus/minus alpha (ablation)RingID · Identification, 2048 keysidentification accuracy (avg): 0.427 -> 0.819Improved
add spatial shift to avoid corner cropping under rotation (ablation)RingID · Identification, 2048 keys, rotationidentification accuracy: 0.000 -> 0.860Improved
add spatial shift (ablation)RingID · Identification, 2048 keys, brightnessidentification accuracy: 0.940 -> 0.870Hurt
add lossless imprinting (ablation)RingID · Identification, 2048 keysidentification accuracy (avg): 0.700 -> 0.819Improved
draw a rounder ring (ablation)RingID · Identification, 2048 keys, rotationidentification accuracy: 0.620 -> 0.860Improved
add Gaussian noise watermark on channel 0 alongside ring watermark (ablation)RingID · Identification, 2048 keysidentification accuracy (avg): 0.740 -> 0.819Improved
imprint noise watermark on channels 0 and 1 instead of channel 0 only (ablation)RingID · Identification, 2048 keysidentification accuracy (avg): 0.819 -> 0.830Improved
imprint noise watermark on channels 0, 1, 2 (ablation)RingID · Identification, 2048 keysidentification accuracy (avg): 0.830 -> 0.807Hurt
use RingID vs Tree-Ring under crop and scale for identificationRingID · Identification, 32 to 2048 keysidentification accuracy: 0.530 -> 0.080 (RingID, 32 to 2048 keys)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy