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 1021–1030 of 1808 papers

TitleStatusHype
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models—0
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack—0
Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation—0
SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation—0
Self adversarial attack as an augmentation method for immunohistochemical stainings—0
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner—0
SELF-KNOWLEDGE DISTILLATION ADVERSARIAL ATTACK—0
Self-Supervised Adversarial Example Detection by Disentangled Representation—0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models—0
Self-Supervised Representation Learning for Adversarial Attack Detection—0
Show:102550
← PrevPage 103 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