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

Showing 14511475 of 1808 papers

TitleStatusHype
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?Code0
Another Dead End for Morphological Tags? Perturbed Inputs and ParsingCode0
Adversarial Attack on Network Embeddings via Supervised Network PoisoningCode0
Evaluating and Understanding the Robustness of Adversarial Logit PairingCode0
Geometry-Aware Generation of Adversarial Point CloudsCode0
Semantic-Aware Adversarial Training for Reliable Deep Hashing RetrievalCode0
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the WildCode0
Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural NetworksCode0
Angelic Patches for Improving Third-Party Object Detector PerformanceCode0
CAAD 2018: Generating Transferable Adversarial ExamplesCode0
TransFool: An Adversarial Attack against Neural Machine Translation ModelsCode0
Translate your gibberish: black-box adversarial attack on machine translation systemsCode0
Graph Adversarial Immunization for Certifiable RobustnessCode0
Graph-based methods coupled with specific distributional distances for adversarial attack detectionCode0
Adversarial Attack on Large Language Models using Exponentiated Gradient DescentCode0
Physics-constrained Attack against Convolution-based Human Motion PredictionCode0
Adversarial Attack on Graph Structured DataCode0
Graph Neural Network Explanations are FragileCode0
Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language ModelsCode0
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial AttackCode0
EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware DetectionCode0
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial AttackCode0
Grey-box Adversarial Attack And Defence For Sentiment ClassificationCode0
Depth-2 Neural Networks Under a Data-Poisoning AttackCode0
ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust AccuraciesCode0
Show:102550
← PrevPage 59 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
5AdvTraining [madry2018]Attack: PGD2048.44Unverified
6TRADES [zhang2019b]Attack: PGD2045.9Unverified
7XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified