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 1481–1490 of 1808 papers

TitleStatusHype
Class-Aware Domain Adaptation for Improving Adversarial Robustness—0
AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack—0
Depth-2 Neural Networks Under a Data-Poisoning AttackCode0
Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution Classifier—0
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability—0
Minority Reports Defense: Defending Against Adversarial Patches—0
Transferable Perturbations of Deep Feature Distributions—0
Enabling Fast and Universal Audio Adversarial Attack Using Generative Model—0
On the Optimal Interaction Range for Multi-Agent Systems Under Adversarial Attack—0
Improved Adversarial Training via Learned Optimizer—0
Show:102550
← PrevPage 149 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