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 1691–1700 of 1808 papers

TitleStatusHype
Optimal Attack against Autoregressive Models by Manipulating the Environment—0
The Efficacy of SHIELD under Different Threat Models—0
Adversarial Metric Attack and Defense for Person Re-identificationCode0
Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models—0
Weighted-Sampling Audio Adversarial Example Attack—0
Theoretically Principled Trade-off between Robustness and AccuracyCode1
Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack—0
Adversarial Attack and Defense on Graph Data: A SurveyCode0
Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors—0
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability—0
Show:102550
← PrevPage 170 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