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 151–175 of 1808 papers

TitleStatusHype
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
Adversarial Attack and Defense in Deep RankingCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
Adversarial Attack and Defense of Structured Prediction ModelsCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving ScenariosCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality MetricsCode1
Are AlphaZero-like Agents Robust to Adversarial Perturbations?Code1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural NetworksCode1
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
Efficient Training of Robust Decision Trees Against Adversarial ExamplesCode1
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustnessCode1
Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a BlinkCode1
3D Gaussian Splat VulnerabilitiesCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
A Review of Adversarial Attack and Defense for Classification MethodsCode1
Show:102550
← PrevPage 7 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