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 641–650 of 1808 papers

TitleStatusHype
Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient EstimationCode0
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit CalibrationCode0
Adversarial Sampling for Fairness Testing in Deep Neural Network—0
Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models—0
AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems—0
Targeted Adversarial Attacks against Neural Machine TranslationCode0
Adversarial Attack with Raindrops—0
Contextual adversarial attack against aerial detection in the physical world—0
Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation—0
HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks—0
Show:102550
← PrevPage 65 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