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 1141–1150 of 1808 papers

TitleStatusHype
A Practical and Stealthy Adversarial Attack for Cyber-Physical Applications—0
Enhanced countering adversarial attacks via input denoising and feature restoringCode0
Fooling Adversarial Training with Inducing Noise—0
Generating Unrestricted 3D Adversarial Point CloudsCode0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models—0
Robust and Effective Grammatical Error Correction with Simple Cycle Self-Augmenting—0
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense—0
BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries—0
Improving the robustness and accuracy of biomedical language models through adversarial trainingCode0
Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks—0
Show:102550
← PrevPage 115 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