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 1326–1350 of 1808 papers

TitleStatusHype
Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds—0
Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series—0
Random Transformation of Image Brightness for Adversarial AttackCode0
Exploring Adversarial Fake Images on Face Manifold—0
Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks—0
Robust Text CAPTCHAs Using Adversarial Examples—0
Local Competition and Stochasticity for Adversarial Robustness in Deep Learning—0
Towards Robustness of Deep Neural Networks via Regularization—0
Consistency-Sensitivity Guided Ensemble Black-Box Adversarial Attacks in Low-Dimensional Spaces—0
Adversarial Attack on Deep Cross-Modal Hamming Retrieval—0
Learn2Weight: Weights Transfer Defense against Similar-domain Adversarial Attacks—0
Black-Box Adversarial Attacks on Graph Neural Networks as An Influence Maximization Problem—0
Stabilized Medical Attacks—0
Identifying Informative Latent Variables Learned by GIN via Mutual Information—0
Practical Order Attack in Deep Ranking—0
Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack—0
AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples—0
Adversarial Example Detection Using Latent Neighborhood Graph—0
An Adversarial Attack via Feature Contributive Regions—0
Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization—0
Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition—0
Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring—0
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks—0
Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis—0
A Hierarchical Feature Constraint to Camouflage Medical Adversarial AttacksCode0
Show:102550
← PrevPage 54 of 73Next →
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