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 976–1000 of 1808 papers

TitleStatusHype
How Private Is Your RL Policy? An Inverse RL Based Analysis FrameworkCode0
Amicable Aid: Perturbing Images to Improve Classification Performance—0
SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization—0
ML Attack Models: Adversarial Attacks and Data Poisoning Attacks—0
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial RobustnessCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
Pyramid Adversarial Training Improves ViT PerformanceCode0
MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack—0
Adaptive Perturbation for Adversarial Attack—0
Adaptive Image Transformations for Transfer-based Adversarial AttackCode0
Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network—0
Thundernna: a white box adversarial attack—0
Heterogeneous Architecture Search Approach within Adversarial Dynamic Defense Framework—0
Metamorphic Adversarial Detection Pipeline for Face Recognition Systems—0
A Practical and Stealthy Adversarial Attack for Cyber-Physical Applications—0
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial TransferabilityCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
Fooling Adversarial Training with Inducing Noise—0
Enhanced countering adversarial attacks via input denoising and feature restoringCode0
A Review of Adversarial Attack and Defense for Classification MethodsCode1
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking TrackersCode1
Generating Unrestricted 3D Adversarial Point CloudsCode0
Robust and Effective Grammatical Error Correction with Simple Cycle Self-Augmenting—0
Input-specific Attention Subnetworks for Adversarial Detection—0
Show:102550
← PrevPage 40 of 73Next →
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