AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Sparse and Imperceivable Adversarial Attacks

Francesco Croce, Matthias Hein

ICCV 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 206 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 CornerSearch instead of SparseFool for l0 attack on MNISTNiN on MNIST · MNISTmedian modified pixels: 12 -> 7Improved
use CornerSearch instead of SparseFool on CIFAR-10NiN on CIFAR-10 · CIFAR-10mean modified pixels: 16.10 -> 2.75Improved
use CornerSearch instead of Pointwise Attack on MNISTNiN on MNIST · MNISTsuccess rate (%): 92.35% -> 97.38%Improved
use CornerSearch instead of SparseFool on Restricted ImageNetResNet-50 · Restricted ImageNetmedian modified pixels: 101 -> 50 median pixels, success 100% -> 93.26%Mixed
use CornerSearch instead of SparseFool under 100 pixel budgetResNet-50 · Restricted ImageNetsuccess rate (%): 49.4% -> 64.0%Improved
add l0 adversarial training (vs plain) against CornerSearch (ablation)CIFAR-10 CNN · CIFAR-10 k=10robust accuracy (%): 2.2 -> 46.0Improved
add l0 adversarial training (vs plain) against CornerSearch (ablation)MNIST CNN · MNIST k=15robust accuracy (%): 9.2 -> 39.8Improved
add linf adversarial training (vs plain) against CornerSearch (ablation)MNIST CNN · MNIST k=15robust accuracy (%): 9.2 -> 0.0Hurt
add l0+sigma adversarial training (vs plain) against sigma-CornerSearch (ablation)MNIST CNN · MNIST k=50robust accuracy (%): 80.4 -> 95.4Improved
add l0+sigma adversarial training (vs plain) against sigma-CornerSearch (ablation)CIFAR-10 CNN · CIFAR-10 k=100robust accuracy (%): 52.4 -> 67.6Improved
use sigma-PGD with smaller kappa instead of the same kappa as sigma-CS (ablation)sigma-PGD · MNIST/CIFAR-10 examplesperturbation visibilityMixed

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