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 911–920 of 1808 papers

TitleStatusHype
Identification of Attack-Specific Signatures in Adversarial Examples—0
Identification of Systematic Errors of Image Classifiers on Rare Subgroups—0
Using Word Embeddings to Explore the Learned Representations of Convolutional Neural Networks—0
Identifying Classes Susceptible to Adversarial Attacks—0
Identifying Informative Latent Variables Learned by GIN via Mutual Information—0
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception—0
IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection—0
IDT: Dual-Task Adversarial Attacks for Privacy Protection—0
A Generative Victim Model for Segmentation—0
ILFO: Adversarial Attack on Adaptive Neural Networks—0
Show:102550
← PrevPage 92 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