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 2650 of 1808 papers

TitleStatusHype
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
Adversarial Self-Supervised Contrastive LearningCode1
Adversarial Ranking Attack and DefenseCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNsCode1
Adversarial Training for Free!Code1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV TrackingCode1
Watch out! Motion is Blurring the Vision of Your Deep Neural NetworksCode1
Adversarial Examples for Semantic Segmentation and Object DetectionCode1
Data-free Universal Adversarial Perturbation with Pseudo-semantic PriorCode1
Adversarial Learning for Robust Deep ClusteringCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
3D Gaussian Splat VulnerabilitiesCode1
Show:102550
← PrevPage 2 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