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 1181–1190 of 1808 papers

TitleStatusHype
NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs—0
Empirical Study of the Decision Region and Robustness in Deep Neural Networks—0
Fooling Adversarial Training with Induction Noise—0
-Weighted Federated Adversarial Training—0
One for Many: an Instagram inspired black-box adversarial attack—0
Linear Backpropagation Leads to Faster Convergence—0
Stochastic Variance Reduced Ensemble Adversarial Attack—0
Adversarially Robust Conformal Prediction—0
Large-Scale Adversarial Attacks on Graph Neural Networks via Graph Coarsening—0
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks—0
Show:102550
← PrevPage 119 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