AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

ARIW-Framework: Adaptive Robust Iterative Watermarking Framework

Shaowu Wu, Liting Zeng, Wei Lu

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network watermarking · 2 citations (OpenAlex)

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 ARIW instead of prior watermarking methods (alpha=1.0)deep watermarking · Mirflickr (D1)average bit accuracy (%): 99.78 -> 99.90 (vs StegaStamp)Improved
compare PSNR to MBRSMBRS · Mirflickr (D1)PSNR (dB): 41.99 -> 42.084Improved
increase embedding strength alpha from 0.2 to 2.0 (ablation)ARIW · Mirflickr (D1)PSNR (dB): 50.48 -> 36.71Hurt
increase embedding strength alpha from 0.2 to 1.0 (ablation)ARIW · Mirflickr (D1)JPEG bit accuracy (%): 75.78 -> 99.66Improved
use image-gradient adaptive embedding strength (ablation)ARIW · Mirflickr (D1)Crop bit accuracy (%): 91.13 -> 99.71Improved
use image-gradient adaptive embedding strength (ablation)ARIW · Mirflickr (D1)JPEG bit accuracy (%): 99.88 -> 99.66No clear effect
initialize iteration at 1 rather than 0 (ablation)ARIW · Mirflickr (D1)Crop bit accuracy (%): 86.21 -> 99.71Improved
vary initial iteration state (original image or noise) (ablation)ARIW · Mirflickr (D1)bit accuracy: 99.71 vs 98.02 vs 99.59 (Crop)No clear effect
use 3x3 kernel instead of 7x7 (ablation)ARIW · Mirflickr (D1)Crop bit accuracy (%): 89.27 -> 99.71Improved
use 3x3 kernel instead of 1x1 (ablation)ARIW · Mirflickr (D1)Crop bit accuracy (%): 95.38 -> 99.71Improved
add CBAM attention to residual (ablation)ARIW · Mirflickr (D1)JPEG bit accuracy (%): 99.66 -> 77.88Hurt
add spatial attention to residual (ablation)ARIW · Mirflickr (D1)JPEG bit accuracy (%): 99.66 -> 93.33Hurt

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