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 991–1000 of 1808 papers

TitleStatusHype
Robust Superpixel-Guided Attentional Adversarial Attack—0
Robust Text CAPTCHAs Using Adversarial Examples—0
Robust Transfer Learning with Pretrained Language Models through Adapters—0
Robust Unpaired Single Image Super-Resolution of Faces—0
Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective—0
Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp—0
ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints—0
SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation—0
SAD: Saliency-based Defenses Against Adversarial Examples—0
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors—0
Show:102550
← PrevPage 100 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