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 226250 of 1808 papers

TitleStatusHype
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
Adversarial Training for Free!Code1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
Physical Adversarial Attack meets Computer Vision: A Decade SurveyCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
Preserving Semantics in Textual Adversarial AttacksCode1
Differentiable JPEG: The Devil is in the DetailsCode1
Proximal Splitting Adversarial Attack for Semantic SegmentationCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
RayS: A Ray Searching Method for Hard-label Adversarial AttackCode1
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural NetworksCode1
Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationCode1
Rethinking Image Restoration for Object DetectionCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Deep Variational Information BottleneckCode1
Defending and Harnessing the Bit-Flip Based Adversarial Weight AttackCode1
Robust Deep Reinforcement Learning through Adversarial LossCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Alleviating Adversarial Attacks on Variational Autoencoders with MCMCCode1
Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless NetworksCode1
Disentangled Information BottleneckCode1
Show:102550
← PrevPage 10 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