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 461–470 of 1808 papers

TitleStatusHype
Boosting Adversarial Transferability of MLP-Mixer—0
Boosting Adversarial Transferability through Enhanced Momentum—0
Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification—0
Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Reality—0
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective—0
Augmented Adversarial Trigger Learning—0
COPYCAT: Practical Adversarial Attacks on Visualization-Based Malware Detection—0
Boosting Black-Box Adversarial Attacks with Meta Learning—0
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors—0
Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References—0
Show:102550
← PrevPage 47 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