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 551–575 of 1808 papers

TitleStatusHype
Adversarial Attack via Dual-Stage Network ErosionCode0
An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelsCode0
An Adversarial Attack Analysis on Malicious Advertisement URL Detection FrameworkCode0
Feature Space Perturbations Yield More Transferable Adversarial ExamplesCode0
An Evasion Attack against Stacked Capsule AutoencoderCode0
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
An Adversarial Approach for Explaining the Predictions of Deep Neural NetworksCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based VisionCode0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
A Multi-task Adversarial Attack Against Face AuthenticationCode0
Explainable Graph Neural Networks Under FireCode0
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate GradientsCode0
Decision-based Universal Adversarial AttackCode0
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial AttacksCode0
Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient EstimationCode0
Evaluating the Validity of Word-level Adversarial Attacks with Large Language ModelsCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement LearningCode0
DD-RobustBench: An Adversarial Robustness Benchmark for Dataset DistillationCode0
Evaluating the Robustness of Adversarial Defenses in Malware Detection SystemsCode0
Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image GenerationCode0
Physics-constrained Attack against Convolution-based Human Motion PredictionCode0
Show:102550
← PrevPage 23 of 73Next →
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