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 391–400 of 1808 papers

TitleStatusHype
Corruption Robust Offline Reinforcement Learning with Human Feedback—0
TETRIS: Towards Exploring the Robustness of Interactive Segmentation—0
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution—0
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks—0
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision TransformersCode0
Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models—0
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on TextCode0
On the Multi-modal Vulnerability of Diffusion ModelsCode1
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign DecodingCode0
STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition—0
Show:102550
← PrevPage 40 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