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 401–410 of 1808 papers

TitleStatusHype
STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition—0
Benchmarking Transferable Adversarial AttacksCode1
AdvGPS: Adversarial GPS for Multi-Agent Perception AttackCode0
Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation—0
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial AttacksCode2
Sparse and Transferable Universal Singular Vectors Attack—0
Fluent dreaming for language modelsCode1
Exploring Adversarial Threat Models in Cyber Physical Battery Systems—0
Susceptibility of Adversarial Attack on Medical Image Segmentation ModelsCode0
HGAttack: Transferable Heterogeneous Graph Adversarial Attack—0
Show:102550
← PrevPage 41 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