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 741–750 of 1808 papers

TitleStatusHype
Learning Transferable Adversarial Robust Representations via Multi-view Consistency—0
Probabilistic Categorical Adversarial Attack & Adversarial Training—0
Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual ExplanationsCode0
Object-Attentional Untargeted Adversarial Attack—0
Dynamics-aware Adversarial Attack of Adaptive Neural NetworksCode0
AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy GradientCode0
Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition—0
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationCode1
Adversarial Attack Against Image-Based Localization Neural Networks—0
FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems—0
Show:102550
← PrevPage 75 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