AI Paper Atlas

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

Margin-based Neural Network Watermarking

Byungjoo Kim, Suyoung Lee, Seanie Lee, Sooel Son, Sung Ju Hwang

ICML 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network 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
margin-based watermarking (maximize trigger-sample margins via projected gradient ascent)source model trained with trigger set · CIFAR-10 / CIFAR-100trigger set accuracy of source model: 100.00 vs 95.67 (RS) and 0 vanillaImproved
margin-based watermarking instead of EWE/RSsoft-label surrogate · CIFAR-10trigger set accuracy of surrogate: 82.00 vs 26.88 (EWE) and 7.67 (RS)Improved
margin-based watermarking instead of EWE/RSsurrogates with hard-label and regularized-GT distillation · CIFAR-10trigger set accuracy of surrogate: 51.33 (hard) and 72.67 (reg w. GT) vs baselines at most 51.01 and 36.05 (EWE) or 7.67 / 6.33 / 3.00 (RS)Improved
margin-based watermarking instead of EWE/RSsurrogate models on CIFAR-100 · CIFAR-100trigger set accuracy of surrogate: 70.67 (soft-label) vs 30.90 (EWE) and 2.67 (RS)Improved
margin-based watermarking instead of EWE/RSsource model accuracy · CIFAR-10clean accuracy of source model: 87.81 vs EWE 86.10 and RS 84.17 but below DI 92.03 and EEF 91.86Mixed
margin-based watermarkingsource model p-value under statistical testing · CIFAR-10p-value of ownership test: 10^-12 vs 10^-7 (EEF) and 10^-3 (DI)Improved
SVHN as surrogate dataset (heterogeneous) (ablation)margin-based watermarked model · CIFAR-10 surrogate with SVHNtrigger set accuracy of surrogate: 72.00 vs 82.00 with CIFAR-10 surrogate dataHurt
VGG11 surrogate architecture instead of ResNet34 (ablation)margin-based watermarked model · CIFAR-10 surrogate with VGG11trigger set accuracy of surrogate: 32.00 vs 82.00 with same-architecture surrogateHurt
randomly chosen trigger-set labels vs highest/lowest confidence labels (ablation)margin-based watermarking · CIFAR-10 trigger labelingsource model trigger accuracy: perfect accuracy on both extreme trigger setsNo clear effect
regularizing surrogate with ground-truth loss (alpha=0.3) (ablation)surrogate model under margin-based watermark · CIFAR-10trigger set accuracy of surrogate: 72.67 vs 82.00 soft-labelNo 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