AI Paper Atlas

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

Morié Attack (MA): A New Potential Risk of Screen Photos

Dantong Niu, Ruohao Guo, Yisen Wang

NeurIPS 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 0 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
simulate camera capture and optimize sensor noise to produce a moiré patternInception-V3 · ImageNet validation, targeted attack, ε=4attack success rate: 0.970Improved
simulate camera capture and optimize sensor noise to produce a moiré patternInception-V3 · ImageNet validation, untargeted attackattack success rate: 1.000Improved
use moiré-pattern perturbations instead of conventional digital attacksImageNet validation, Inception-V3 · untargeted attack, JPEG qf=20attack success rate: 0.286 -> 0.938 (BIM); 0.276 -> 0.938 (PGD); 0.491 -> 0.938 (MI-FGSM)Improved
generate perturbations through the camera pipeline rather than adding them after demosaicing (ablation)Moiré Attack · ImageNet validation, untargeted attack, JPEG compressionattack success rate: 0.857 -> 0.938 (qf=20); 0.902 -> 0.949 (qf=40)Improved
increase sensor-noise budget (ablation)Moiré Attack · ImageNet validation, targeted attackattack success rate: 0.876 -> 0.970 -> 0.990 -> 0.995Improved
increase sensor-noise budget (ablation)Moiré Attack · ImageNet validation, untargeted attackattack success rate: 1.000 -> 1.000 -> 1.000 -> 1.000No clear effect
mean-value normalize the generated examples (ablation)Moiré Attack · ImageNet validation, untargeted attack, ε=4attack success rate: 1.000 -> 0.987Hurt
apply JPEG compression to generated adversarial examplesMoiré Attack · ImageNet validation, untargeted attack, ε=4attack success rate: 1.000 -> 0.938 (qf=20); 1.000 -> 0.949 (qf=40); 1.000 -> 0.956 (qf=60); 1.000 -> 0.9881 (qf=80)Hurt
apply demoiréing preprocessingMoiré Attack · ImageNet validation, untargeted attack, ε=4attack success rate: 1.000 -> 0.989 (MopNet); 0.997 (MDDM); 1.000 (FHde2Net); 0.974 (AMNet)Mixed
transfer the attack from Inception-V3 to other architecturesMoiré Attack · ImageNet validation, ε=4 untargeted attackattack success rate: 0.967 (ResNet50); 0.927 (ResNet34); 0.959 (DenseNet121); 0.982 (VGG16); 0.973 (VGG19)Improved
increase the monitor display size scale factor (ablation)Moiré Attack · synthesized moiré patternmoiré distortionImproved
vary the simulated camera rotation angle (ablation)Moiré Attack · synthesized moiré patternpattern appearanceMixed

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