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 961–970 of 1808 papers

TitleStatusHype
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching—0
Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing—0
Unauthorized AI cannot Recognize Me: Reversible Adversarial Example—0
Reversible Attack based on Local Visual Adversarial Perturbation—0
Reversible Adversarial Attack based on Reversible Image Transformation—0
Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective—0
Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers—0
Rigid Body Adversarial Attacks—0
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search—0
Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation—0
Show:102550
← PrevPage 97 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