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 251275 of 1808 papers

TitleStatusHype
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
Sparse Adversarial Video Attacks with Spatial TransformationsCode1
Distributionally Adversarial AttackCode1
Square Attack: a query-efficient black-box adversarial attack via random searchCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability DetectionCode1
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustnessCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial DistributionCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical FlowCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural NetworksCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based RetrievalCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution LearningCode1
Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and BeyondCode1
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression RecognitionCode1
Fluent dreaming for language modelsCode1
Geometric Adversarial Attacks and Defenses on 3D Point CloudsCode1
Show:102550
← PrevPage 11 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