AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Data-Free Universal Adversarial Perturbation and Black-Box Attack

Chaoning Zhang, Philipp Benz, Adil Karjauv, In So Kweon

ICCV 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 75 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
use CosSim minimization loss instead of CosSim-max (ablation)Cosine-UAP · ImageNet val (ResNet152)fooling ratio: 80.2 -> 90.2Improved
use CosSim loss instead of CosSim-max (ablation)Cosine-UAP · ImageNet val (VGG19)fooling ratio: 91.1 -> 96.4Improved
use jigsaw images with variable frequency instead of fixed frequency (ablation)Data-free Cosine-UAP · ImageNet val (avg 5 models)fooling ratio: 79.4 -> 84.08Improved
use jigsaw images instead of Gaussian noise (ablation)Data-free Cosine-UAP · ImageNet val (avg 5 models)fooling ratio: 67.9 -> 84.08Improved
use jigsaw images instead of flat images (ablation)Data-free Cosine-UAP · ImageNet val (avg 5 models)fooling ratio: 62.1 -> 84.08Improved
randomly resize the UAP during training (ablation)Cosine-UAP · ImageNet val (224 input)fooling ratio: 89.48 -> 86.16Hurt
randomly resize the UAP during training (ablation)Cosine-UAP · ImageNet val (112 input)fooling ratio: 58.57 -> 62.05Improved
randomly resize the UAP during training (transfer VGG16 to ResNet152) (ablation)Cosine-UAP · ImageNet valfooling ratio: 38.37 -> 44.27Improved
remove high-frequency content with Fourier transformcheckerboard attack · ImageNet black-boxaccuracy under attack: 25.3% -> 20.8%Improved
use checkerboard instead of uniform noise pattern (no HF removal)optimization-free attack · ImageNet black-boxaccuracy under attack: 67.3% -> 25.3%Improved
use optimization-free checkerboard instead of Prototypical*data-free black-box attack · ImageNet black-boxaccuracy under attack: 31.2% -> 25.3%Improved
reduce training samples from full set to 32 with augmentationCosine-UAP · ImageNet val (VGG16)fooling ratio: 97.4 -> 93.5Hurt

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