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
Adversarial Patch Attacks on Monocular Depth Estimation Networks—0
Second-Order NLP Adversarial ExamplesCode0
A Study for Universal Adversarial Attacks on Texture Recognition—0
Adversarial Attack and Defense of Structured Prediction ModelsCode1
CorrAttack: Black-box Adversarial Attack with Structured Search—0
A Deep Genetic Programming based Methodology for Art Media Classification Robust to Adversarial Perturbations—0
An alternative proof of the vulnerability of retrieval in high intrinsic dimensionality neighborhood—0
Adversarial Attacks Against Deep Learning Systems for ICD-9 Code Assignment—0
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations—0
Improving Query Efficiency of Black-box Adversarial AttackCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers—0
Stereopagnosia: Fooling Stereo Networks with Adversarial PerturbationsCode1
Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading—0
Adversarial Rain Attack and Defensive Deraining for DNN Perception—0
Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations—0
Bias Field Poses a Threat to DNN-based X-Ray Recognition—0
Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object DetectionCode1
OpenAttack: An Open-source Textual Adversarial Attack ToolkitCode1
MultAV: Multiplicative Adversarial Videos—0
Label Smoothing and Adversarial Robustness—0
Contextualized Perturbation for Textual Adversarial AttackCode1
Decision-based Universal Adversarial AttackCode0
Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial AttacksCode0
Input Hessian Regularization of Neural Networks—0
Show:102550
← PrevPage 54 of 73Next →
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