AI Paper Atlas

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

Robust Watermarking for Deep Neural Networks via Bi-Level Optimization

Peng Yang, Yingjie Lao, Ping Li

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network watermarking · 65 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
increase number of embedded keys from 5 to 20 on ImageNet (ablation)Proposed bi-level watermarking · ImageNet (Inception-V3)Rauth: 100% -> 97.5%Hurt
increase number of embedded keys from 5 to 20 on ImageNet (ablation)Proposed bi-level watermarking · ImageNet (Inception-V3)Rloss: 0.07% -> 0.15%Hurt
increase number of embedded keys from 5 to 20 on MNIST (ablation)Proposed bi-level watermarking · MNIST (LeNet5)Rloss: 0.00% -> 0.07%Hurt
use bi-level robust watermarking instead of white-box method [9]DNN watermarking on CIFAR10 · CIFAR10 overwriting, 20 keysRloss: ∼0.5% -> ∼0.05%Improved
use bi-level robust watermarking instead of backdoor black-box method [1]DNN watermarking on CIFAR10 · CIFAR10 overwriting, 20 keysRpres: 95% -> 100%Improved
use bi-level robust watermarking instead of white-box method [9]DNN watermarking on CIFAR10 · CIFAR10 overwriting, 20 keysRpres: 58% -> 100%Improved
apply pruning up to 50% rate on the watermarked modelProposed bi-level watermarking · CIFAR10 pruningidentification accuracy: 50%No clear effect
embed keys one by one instead of all at once under sequential overwritingProposed bi-level watermarking · CIFAR10/100 and ImageNet overwritingsignature preserve rate: 95% and 100%Mixed
embed 60 keys instead of fewer keys (capacity test)Proposed bi-level watermarking · MNIST, CIFAR10, CIFAR100 capacityauthentication rate / function preserve rate: more than 94% auth, around 99.0% function preserve at 60 keysHurt

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