SOTAVerified

Adversarial Attack

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1171–1180 of 1808 papers

TitleStatusHype
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration—0
On-Manifold Projected Gradient Descent—0
On Neural Network approximation of ideal adversarial attack and convergence of adversarial training—0
Towards more transferable adversarial attack in black-box manner—0
Adversarial Attacks and Defenses: An Interpretation Perspective—0
Challenging the adversarial robustness of DNNs based on error-correcting output codes—0
Adversarially Robust Neural Architectures—0
Towards Natural Robustness Against Adversarial Examples—0
On the Effectiveness of Low Frequency Perturbations—0
On the existence of consistent adversarial attacks in high-dimensional linear classification—0
Show:102550
← PrevPage 118 of 181Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68—Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
4AdvTraining [madry2018]Attack: PGD2048.44—Unverified
5TRADES [zhang2019b]Attack: PGD2045.9—Unverified
6XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified