AI Paper Atlas

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

GreedyFool: Distortion-Aware Sparse Adversarial Attack

Xiaoyi Dong, Dongdong Chen, Jianmin Bao, Chuan Qin, Lu Yuan, Weiming Zhang, Nenghai Yu, Dong Chen

NeurIPS 2020 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 12 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 the Reduce stage that drops redundant pixels (ablation)GreedyFool · ImageNet eps=10mean perturbed pixels: 537.10 -> 426.77Improved
add GAN-based distortion map guidance (ablation)GreedyFool · ImageNet eps=10binary classifier accuracy (lower is more invisible): 75.65 -> 68.50Improved
add distortion map guidance (ablation)GreedyFool · ImageNet eps=10mean perturbed pixels: 537.10 -> 607.22Hurt
use gradient magnitude and sign instead of only gradient sign (ablation)GreedyFool · ImageNet eps=10mean perturbed pixels: 1149.39 -> 537.10Improved
use GreedyFool instead of SparseFool for non-target sparse attackGreedyFool · ImageNet eps=255median perturbed pixels: 80.50 -> 27.00Improved
use GreedyFool instead of PGD0 for target attack with 200 pixel budget on ImageNetGreedyFool · ImageNet target attack eps=255success rate (%): 5.56 -> 15.52Improved
use GreedyFool instead of PGD0 for single-pixel non-target attack on CIFAR10GreedyFool · CIFAR10 eps=255 m=1fooling rate (%): 15.22 -> 12.41Hurt
increase confidence factor kappa from 0 to 6 in the Increasing stage only (ablation)GreedyFool · ImageNet black-box transfer DenseNet161->ResNet50fooling rate (%): 17.00 -> 32.33Improved
use GreedyFool instead of PGD0 on ImageNet runtimeGreedyFool · ImageNetseconds per image: 3.232 -> 5.253Hurt
use GreedyFool instead of SparseFool for invisibility against SRM detectorGreedyFool · ImageNet eps=255SRM detection rate (%): 74.36 -> 61.54Improved

Later papers that compared with this method

2 later accepted papers report GreedyFool (κ=15) as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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