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 176200 of 1808 papers

TitleStatusHype
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural NetworksCode1
Adversarial Immunization for Certifiable Robustness on GraphsCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
Efficient Training of Robust Decision Trees Against Adversarial ExamplesCode1
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression RecognitionCode1
Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a BlinkCode1
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query AttacksCode1
Adversarial Learning for Robust Deep ClusteringCode1
Adversarial Attack on Community Detection by Hiding IndividualsCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial AttackCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
Fluent dreaming for language modelsCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Fusing Event-based and RGB camera for Robust Object Detection in Adverse ConditionsCode1
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative modelCode1
Adversarial Attack on Graph Neural Networks as An Influence Maximization ProblemCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Geometric Adversarial Attacks and Defenses on 3D Point CloudsCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Show:102550
← PrevPage 8 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