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 1591–1600 of 1808 papers

TitleStatusHype
A Survey on Physical Adversarial Attacks against Face Recognition Systems—0
Constrained Adversarial Learning for Automated Software Testing: a literature review—0
Constrained Network Adversarial Attacks: Validity, Robustness, and Transferability—0
Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories—0
Content-based Unrestricted Adversarial Attack—0
Context-aware Adversarial Attack on Named Entity Recognition—0
Contextual adversarial attack against aerial detection in the physical world—0
A Survey on Physical Adversarial Attack in Computer Vision—0
Contrastive Weighted Learning for Near-Infrared Gaze Estimation—0
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack—0
Show:102550
← PrevPage 160 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