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 1311–1320 of 1808 papers

TitleStatusHype
L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set—0
Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic TradersCode1
Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing—0
Generalizing Universal Adversarial Attacks Beyond Additive PerturbationsCode1
A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning—0
Explain2Attack: Text Adversarial Attacks via Cross-Domain InterpretabilityCode0
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial AttackCode0
Towards Resistant Audio Adversarial ExamplesCode1
An Evasion Attack against Stacked Capsule AutoencoderCode0
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks—0
Show:102550
← PrevPage 132 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