AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Model Watermarking for Image Processing Networks

Jie Zhang, Dongdong Chen, Jing Liao, Han Fang, Weiming Zhang, Wenbo Zhou, Hao Cui, Nenghai Yu

AAAI 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Data-free substitute training · 137 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 deep invisible image watermarking instead of traditional spatial bit watermarkingImage-processing model watermarking · Debone and derain, surrogate models with different architecturessuccess rate: 0% -> 100%Improved
Add adversarial training for the watermark extractor (ablation)Deep invisible watermarking framework · Debone and derain, UNet + L2 surrogatesuccess rate: 0% -> 100%Improved
Add a clean loss that trains the extractor to return blank on watermark-free images (ablation)Watermark extractor · Clean images from domains A and Bfalse watermark extractionImproved
Add a consistent loss across extracted watermarks (ablation)Watermark extractor · Watermarked outputs including surrogate outputswatermark extraction qualityImproved
Combine task-specific image processing with watermark embedding in HDebone model · DebonePSNR: 25.81 -> 24.49Hurt
Combine task-specific image processing with watermark embedding in HDebone model · DeboneSSIM: 0.91 -> 0.91No clear effect
Remove adversarial training (ablation)Deep invisible watermarking framework · Surrogate models trained with L2 losssuccess rate: 100% -> 0%Hurt

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