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 51–60 of 1808 papers

TitleStatusHype
EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability DetectionCode1
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous DrivingCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation ModelsCode1
Universal Adversarial Perturbations for Vision-Language Pre-trained ModelsCode1
Revisiting Character-level Adversarial Attacks for Language ModelsCode1
Show:102550
← PrevPage 6 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