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 251–300 of 1808 papers

TitleStatusHype
Maximum Mean Discrepancy Test is Aware of Adversarial AttacksCode1
Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic TradersCode1
Generalizing Universal Adversarial Attacks Beyond Additive PerturbationsCode1
Towards Resistant Audio Adversarial ExamplesCode1
Adversarial Attack and Defense of Structured Prediction ModelsCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Improving Query Efficiency of Black-box Adversarial AttackCode1
Stereopagnosia: Fooling Stereo Networks with Adversarial PerturbationsCode1
OpenAttack: An Open-source Textual Adversarial Attack ToolkitCode1
Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object DetectionCode1
Contextualized Perturbation for Textual Adversarial AttackCode1
Adversarial Attack on Large Scale GraphCode1
Adversarial Attack and Defense Strategies for Deep Speaker Recognition SystemsCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
Robust Deep Reinforcement Learning through Adversarial LossCode1
SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image EditingCode1
SimAug: Learning Robust Representations from Simulation for Trajectory PredictionCode1
Sparse Adversarial Attack via Perturbation FactorizationCode1
Robust Tracking against Adversarial AttacksCode1
Semantic Equivalent Adversarial Data Augmentation for Visual Question AnsweringCode1
Adversarial Immunization for Certifiable Robustness on GraphsCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
Patch-wise Attack for Fooling Deep Neural NetworkCode1
Miss the Point: Targeted Adversarial Attack on Multiple Landmark DetectionCode1
Black-box Adversarial Example Generation with Normalizing FlowsCode1
RayS: A Ray Searching Method for Hard-label Adversarial AttackCode1
Differentiable Language Model Adversarial Attacks on Categorical Sequence ClassifiersCode1
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial DistributionCode1
Adversarial Self-Supervised Contrastive LearningCode1
Targeted Adversarial Perturbations for Monocular Depth PredictionCode1
Interpolation between Residual and Non-Residual NetworksCode1
Pick-Object-Attack: Type-Specific Adversarial Attack for Object DetectionCode1
Defending and Harnessing the Bit-Flip Based Adversarial Weight AttackCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
On Intrinsic Dataset Properties for Adversarial Machine LearningCode1
Defending Your Voice: Adversarial Attack on Voice ConversionCode1
Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspectiveCode1
Attacking Recommender Systems with Augmented User ProfilesCode1
BayesOpt Adversarial AttackCode1
Sign Bits Are All You Need for Black-Box AttacksCode1
Towards Feature Space Adversarial AttackCode1
BERT-ATTACK: Adversarial Attack Against BERT Using BERTCode1
Adversarial Attack on Deep Learning-Based Splice LocalizationCode1
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-RankingCode1
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible NoisesCode1
Motion-Excited Sampler: Video Adversarial Attack with Sparked PriorCode1
Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation SystemsCode1
Adversarial Ranking Attack and DefenseCode1
Stabilizing Differentiable Architecture Search via Perturbation-based RegularizationCode1
Watch out! Motion is Blurring the Vision of Your Deep Neural NetworksCode1
Show:102550
← PrevPage 6 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