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 1351–1360 of 1808 papers

TitleStatusHype
Learn2Weight: Weights Transfer Defense against Similar-domain Adversarial Attacks—0
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations—0
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing—0
Learning Globally Optimized Language Structure via Adversarial Training—0
Learning Key Steps to Attack Deep Reinforcement Learning Agents—0
Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations—0
Learning to Defend by Learning to Attack—0
Learning to Defense by Learning to Attack—0
Learning to Detect Adversarial Examples Based on Class Scores—0
Left-right Discrepancy for Adversarial Attack on Stereo Networks—0
Show:102550
← PrevPage 136 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