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

Showing 176200 of 1808 papers

TitleStatusHype
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
Triangle Attack: A Query-efficient Decision-based Adversarial AttackCode1
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial RobustnessCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial TransferabilityCode1
A Review of Adversarial Attack and Defense for Classification MethodsCode1
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking TrackersCode1
Sparse Adversarial Video Attacks with Spatial TransformationsCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack FrameworkCode1
Boosting the Transferability of Video Adversarial Examples via Temporal TranslationCode1
Unrestricted Adversarial Attacks on ImageNet CompetitionCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferCode1
Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated LearningCode1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNsCode1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial AttackCode1
FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial AttackCode1
PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification ModelsCode1
Multi-granularity Textual Adversarial Attack with Behavior CloningCode1
DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural NetworksCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Show:102550
← PrevPage 8 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified