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

Showing 101125 of 1808 papers

TitleStatusHype
Adversarial Attack on Large Scale GraphCode1
On the Multi-modal Vulnerability of Diffusion ModelsCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
Augmented Lagrangian Adversarial AttacksCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
Alleviating Adversarial Attacks on Variational Autoencoders with MCMCCode1
3D Adversarial Attacks Beyond Point CloudCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural NetworksCode1
Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face RecognitionCode1
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial AttackCode1
Show:102550
← PrevPage 5 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified