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 541–550 of 1808 papers

TitleStatusHype
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification—0
GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization—0
DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies—0
Evaluating the Validity of Word-level Adversarial Attacks with Large Language ModelsCode0
A Multi-task Adversarial Attack Against Face AuthenticationCode0
Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation—0
Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack—0
ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack—0
Improving Network Interpretability via Explanation Consistency Evaluation—0
Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis—0
Show:102550
← PrevPage 55 of 181Next →
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