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 1101–1150 of 1808 papers

TitleStatusHype
Model Leeching: An Extraction Attack Targeting LLMs—0
Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems—0
MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework—0
Moshi Moshi? A Model Selection Hijacking Adversarial Attack—0
Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning—0
Moving Target Defense Against Adversarial False Data Injection Attacks In Power Grids—0
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification—0
MultAV: Multiplicative Adversarial Videos—0
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition—0
Multiclass ASMA vs Targeted PGD Attack in Image Segmentation—0
Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency—0
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models—0
Adversarial Sampling for Fairness Testing in Deep Neural Network—0
Towards Building a Robust Toxicity Predictor—0
Multi-head Uncertainty Inference for Adversarial Attack Detection—0
Towards Calibration Enhanced Network by Inverse Adversarial Attack—0
Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations—0
Multi-step domain adaptation by adversarial attack to H ΔH-divergence—0
Multi-Task Adversarial Attack—0
Adversarial Robustness through Dynamic Ensemble Learning—0
Mutual-modality Adversarial Attack with Semantic Perturbation—0
NATTACK: A STRONG AND UNIVERSAL GAUSSIAN BLACK-BOX ADVERSARIAL ATTACK—0
Towards Certified Defense for Unrestricted Adversarial Attacks—0
Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons—0
Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data—0
Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty—0
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses—0
NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields—0
Adversarial Robustness for Deep Learning-based Wildfire Prediction Models—0
ADMM based Distributed State Observer Design under Sparse Sensor Attacks—0
Mitigating Deep Learning Vulnerabilities from Adversarial Examples Attack in the Cybersecurity Domain—0
Vulnerability of Deep Learning—0
Neural Networks Playing Dough: Investigating Deep Cognition With a Gradient-Based Adversarial Attack—0
Adversarial Relighting Against Face Recognition—0
Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition—0
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer—0
NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs—0
Wasserstein Adversarial Examples on Univariant Time Series Data—0
Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task—0
Adversarial Attack for Asynchronous Event-based Data—0
NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models—0
A Differentiable Language Model Adversarial Attack on Text Classifiers—0
Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models—0
Nonconvex Zeroth-Order Stochastic ADMM Methods with Lower Function Query Complexity—0
No Query, No Access—0
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks—0
Fooling Network Interpretation in Image Classification—0
An alternative proof of the vulnerability of retrieval in high intrinsic dimensionality neighborhood—0
Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks—0
Now You See It, Now You Dont: Adversarial Vulnerabilities in Computational Pathology—0
Show:102550
← PrevPage 23 of 37Next →
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