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 1291–1300 of 1808 papers

TitleStatusHype
Protein Folding Neural Networks Are Not Robust—0
Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification—0
Adversarial Eigen Attack on Black-Box Models—0
Adversarial defenses via a mixture of generators—0
Adversarial Defense based on Structure-to-Signal Autoencoders—0
Pseudo-Conversation Injection for LLM Goal Hijacking—0
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks—0
Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation—0
QFAL: Quantum Federated Adversarial Learning—0
Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models—0
Show:102550
← PrevPage 130 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