AI Paper Atlas

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

The LogBarrier Adversarial Attack: Making Effective Use of Decision Boundary Information

Chris Finlay, Aram-Alexandre Pooladian, Adam Oberman

ICCV 2019 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 29 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 LogBarrier instead of PGD (l2)l2 attack · MNISTpercent misclassified: 52.58 -> 99.10Improved
use LogBarrier instead of CW (l2)l2 attack · CIFAR10 ResNeXt34percent misclassified: 90.40 -> 99.90Improved
use LogBarrier instead of CW (l2)l2 attack · ImageNet-1Kpercent misclassified: 74.86 -> 98.40Improved
use LogBarrier instead of PGD (l2)l2 attack · ImageNet-1Kpercent misclassified: 90.00 -> 98.40Hurt
use LogBarrier instead of IFGSM (linf)linf attack · MNISTpercent misclassified: 73.40 -> 94.80Improved
use LogBarrier instead of IFGSM (linf)linf attack · CIFAR10 ResNeXt34percent misclassified: 75.80 -> 98.70Improved
use LogBarrier instead of IFGSM (linf)linf attack · ImageNet-1Kpercent misclassified: 99.60 -> 95.20Hurt
use LogBarrier instead of IFGSM against softmax-temperature obfuscation (MNIST)linf attack · MNIST obfuscated (T = 2)percent misclassified at linf 0.3: 32.90 -> 99.80Improved
use LogBarrier instead of IFGSM against softmax-temperature obfuscation (CIFAR10)linf attack · CIFAR10 obfuscated (T = 20)percent misclassified at linf 8/255: 43.90 -> 54.40Improved
use LogBarrier instead of IFGSM against adversarial training (MNIST)linf attack · MNIST adversarially trainedlinf distance to perturb 90% of images: 6.51E-1 -> 2.85E-1Improved
add multi-step adversarial training to the MNIST model (ablation)MNIST net · MNIST, LogBarrier attacklinf distance to perturb 90% of images: 2.27E-1 -> 2.85E-1No clear effect
use LogBarrier instead of IFGSM on adversarially trained model (CIFAR10)linf attack · CIFAR10 adversarial trainingpercent misclassified at linf 4/255: 31.60 -> 23.40Hurt

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