AI Paper Atlas

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

Deep Model Intellectual Property Protection via Deep Watermarking

Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Huamin Feng, Gang Hua, Nenghai Yu

TPAMI 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network watermarking · 146 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
add adversarial training stage for the extractor (ablation)Debone-IEEE watermark · Debone surrogate attack (UNet, L2)SR_NC: 27% -> 100%Improved
add adversarial training stage for the extractor (ablation)Debone-IEEE watermark · Debone surrogate attack (CNet, L2)SR_NC: 0% -> 93%Improved
add adversarial training stage for the extractor (ablation)Derain-Flower watermark · Derain surrogate attack (UNet, L2+L_adv)SR_NC: 0% -> 99%Improved
add clean loss on watermark-free images (ablation)extractor R · watermark-free imagesfalse extractionImproved
add watermark consistent loss (ablation)extractor R · surrogate outputsextraction qualityImproved
add overwriting-aware enhanced training with re-watermark noise layer (ablation)extractor R · Watermark overwriting (Flower)SR_NC: 0% -> 100%Improved
increase surrogate CNet channels from 8 to 256 (ablation)Debone watermark extractor · Debone CNet surrogateSR_NC: 3% -> 99%Improved
increase lambda from 0.1 to 10 (ablation)Debone-IEEE · Debone-IEEEPSNR: 49.82 -> 43.21Hurt
vary watermark size from 32 to 256 (ablation)Debone-IEEE · Debone-IEEEPSNR: 46.89 -> 47.29No clear effect
embed multiple watermarks in one network (ablation)Debone_IEEE · Debone-IEEEPSNR: 47.76 -> 41.87Hurt
replace spatial invisible watermarking with deep invisible watermark networkTSIW-64 · Debone surrogate attack (CNet)SR_NC: 0% -> 93%Improved
make target model self-watermarked instead of adding barrierDerain model · DerainPSNR: 32.49 -> 32.13No 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