AI Paper Atlas

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

CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising

Puneet Gupta, Esa Rahtu

ICCV 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 58 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 class-specific inpainting to wavelet denoising (ablation)Wavelet denoiser · ImageNet 500-image train set, FGSMtop-1 accuracy: 39.2% -> 87.6%Improved
add class-specific inpainting to wavelet denoising (ablation)Wavelet denoiser · ImageNet 500-image train set, IGSMtop-1 accuracy: 30.4% -> 93.8%Improved
add wavelet denoising to class-specific inpainting (ablation)Inpainting only · ImageNet 500-image train set, FGSMtop-1 accuracy: 78.2% -> 87.6%Improved
add wavelet denoising to class-specific inpainting (ablation)Inpainting only · ImageNet 500-image train set, clean imagestop-1 accuracy: 98.2% -> 99.2%Improved
replace image quilting with class-specific inpainting (ablation)Quilting · ImageNet 500-image train set, clean imagestop-1 accuracy: 74.2% -> 98.2%Improved
replace image quilting with class-specific inpainting (ablation)Quilting · ImageNet 500-image train set, FGSMtop-1 accuracy: 68.4% -> 78.2%Improved
replace JPEG compression with wavelet denoising when combined with inpainting (ablation)Inpainting + JPEG · ImageNet 500-image train set, FGSMtop-1 accuracy: 81.6% -> 87.6%Improved
add inpainting to JPEG compression (ablation)JPEG · ImageNet 500-image train set, FGSMtop-1 accuracy: 35.8% -> 81.6%Improved
apply CIIDefence to clean imagesResNet-101 · ImageNet valtop-1 accuracy: 100% -> 98.6%Hurt
add CIIDefence under FGSMResNet-101 · ImageNet val FGSMtop-1 accuracy: 18.9% -> 85.7%Improved
add CIIDefence under PGDResNet-101 · ImageNet val PGDtop-1 accuracy: 0% -> 97.8%Improved
use CIIDefence instead of PD with wavelet denoisingPD + wavelet [23] · ImageNet val FGSMdestruction rate: 0.638 -> 0.822Improved

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