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 201–250 of 1808 papers

TitleStatusHype
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Meta Gradient Adversarial AttackCode1
Poison Ink: Robust and Invisible Backdoor AttackCode1
Discriminator-Free Generative Adversarial AttackCode1
Adversarial Attack on Graph Neural Networks as An Influence Maximization ProblemCode1
TDGIA:Effective Injection Attacks on Graph Neural NetworksCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
On Improving Adversarial Transferability of Vision TransformersCode1
Adversarial Attack and Defense in Deep RankingCode1
Transferable Sparse Adversarial AttackCode1
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating DeepfakesCode1
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural NetworksCode1
Improving Adversarial Transferability with Gradient RefiningCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
3D Adversarial Attacks Beyond Point CloudCode1
Staircase Sign Method for Boosting Adversarial AttacksCode1
R&R: Metric-guided Adversarial Sentence GenerationCode1
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness VerificationCode1
Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a BlinkCode1
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial AttackCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier DomainCode1
A Survey On Universal Adversarial AttackCode1
Online Adversarial AttacksCode1
Targeted Attack against Deep Neural Networks via Flipping Limited Weight BitsCode1
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningCode1
Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryCode1
Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android AppsCode1
Patch-wise++ Perturbation for Adversarial Targeted AttacksCode1
Sparse Adversarial Attack to Object DetectionCode1
Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationCode1
Efficient Training of Robust Decision Trees Against Adversarial ExamplesCode1
Disentangled Information BottleneckCode1
SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image ClassifiersCode1
Composite Adversarial AttacksCode1
Geometric Adversarial Attacks and Defenses on 3D Point CloudsCode1
Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object DetectionCode1
Adversarial Learning for Robust Deep ClusteringCode1
Guided Adversarial Attack for Evaluating and Enhancing Adversarial DefensesCode1
SurFree: a fast surrogate-free black-box attackCode1
Augmented Lagrangian Adversarial AttacksCode1
FoolHD: Fooling speaker identification by Highly imperceptible adversarial DisturbancesCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Single-Node Attacks for Fooling Graph Neural NetworksCode1
Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery DetectionCode1
Object Hider: Adversarial Patch Attack Against Object DetectorsCode1
GreedyFool: Distortion-Aware Sparse Adversarial AttackCode1
Maximum Mean Discrepancy Test is Aware of Adversarial AttacksCode1
Show:102550
← PrevPage 5 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