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 621–630 of 1808 papers

TitleStatusHype
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack—0
Adversarial Attacks and Dimensionality in Text Classifiers—0
Patch Synthesis for Property Repair of Deep Neural Networks—0
READ: Improving Relation Extraction from an ADversarial PerspectiveCode0
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models—0
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models—0
The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness—0
Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks—0
Deep Learning for Robust and Explainable Models in Computer Vision—0
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection—0
Show:102550
← PrevPage 63 of 181Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68—Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
5AdvTraining [madry2018]Attack: PGD2048.44—Unverified
6TRADES [zhang2019b]Attack: PGD2045.9—Unverified
7XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified