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 101–150 of 1808 papers

TitleStatusHype
Adversarial Self-Supervised Contrastive LearningCode1
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial DistributionCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning ModelsCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical FlowCode1
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution LearningCode1
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness VerificationCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
Black-box Adversarial Example Generation with Normalizing FlowsCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object TrackingCode1
Frequency Domain Adversarial Training for Robust Volumetric Medical SegmentationCode1
A Survey On Universal Adversarial AttackCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial AttackCode1
Attacking Recommender Systems with Augmented User ProfilesCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
BayesOpt Adversarial AttackCode1
Boosting Adversarial Transferability via Gradient Relevance AttackCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsCode1
Adversarial Immunization for Certifiable Robustness on GraphsCode1
Adversarial Learning for Robust Deep ClusteringCode1
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake DetectionCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
BERT-ATTACK: Adversarial Attack Against BERT Using BERTCode1
3D Adversarial Attacks Beyond Point CloudCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
Adversarial Ranking Attack and DefenseCode1
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationCode1
Fooling the Image Dehazing Models by First Order GradientCode1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNsCode1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Show:102550
← PrevPage 3 of 37Next →
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