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 471–480 of 1808 papers

TitleStatusHype
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?—0
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language ModelCode0
Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan ScriptCode0
Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks—0
Intermediate Outputs Are More Sensitive Than You Think—0
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving—0
Fall Leaf Adversarial Attack on Traffic Sign Classification—0
Scaling Laws for Black box Adversarial Attacks—0
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack—0
Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation—0
Show:102550
← PrevPage 48 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