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 651–700 of 1808 papers

TitleStatusHype
Curls & Whey: Boosting Black-Box Adversarial AttacksCode0
Model-Agnostic Defense for Lane Detection against Adversarial AttackCode0
Adversarial and Clean Data Are Not TwinsCode0
CT-GAT: Cross-Task Generative Adversarial Attack based on TransferabilityCode0
Rob-GAN: Generator, Discriminator, and Adversarial AttackerCode0
Cross-lingual Cross-temporal Summarization: Dataset, Models, EvaluationCode0
Adversarial Attacks on Gaussian Process BanditsCode0
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single ImageCode0
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation FrameworkCode0
GenAttack: Practical Black-box Attacks with Gradient-Free OptimizationCode0
2D-Malafide: Adversarial Attacks Against Face Deepfake Detection SystemsCode0
Neural Fingerprints for Adversarial Attack DetectionCode0
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of ArtifactsCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage GenerationCode0
Noise-based cyberattacks generating fake P300 waves in brain–computer interfacesCode0
Robustness for Non-Parametric Classification: A Generic Attack and DefenseCode0
DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural NetworksCode0
FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMsCode0
Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial AttackCode0
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation TechniquesCode0
Adversarial Attacks on Deep Neural Networks for Time Series ClassificationCode0
FireBERT: Hardening BERT-based classifiers against adversarial attackCode0
Foiling Explanations in Deep Neural NetworksCode0
Controversial stimuli: pitting neural networks against each other as models of human recognitionCode0
AICAttack: Adversarial Image Captioning Attack with Attention-Based OptimizationCode0
Dynamic Transformers Provide a False Sense of EfficiencyCode0
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial ExamplesCode0
FDA: Feature Disruptive AttackCode0
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over SimplexCode0
A Hierarchical Feature Constraint to Camouflage Medical Adversarial AttacksCode0
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality MetricsCode0
Fast Inference of Removal-Based Node InfluenceCode0
Efficient and Transferable Adversarial Examples from Bayesian Neural NetworksCode0
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function PriorCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Efficient Robust Conformal Prediction via Lipschitz-Bounded NetworksCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
Explainable and Safe Reinforcement Learning for Autonomous Air MobilityCode0
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selectionCode0
Excess Capacity and Backdoor PoisoningCode0
Expanding Scope: Adapting English Adversarial Attacks to ChineseCode0
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial AttackCode0
Explainable Graph Neural Networks Under FireCode0
Feature Space Perturbations Yield More Transferable Adversarial ExamplesCode0
Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color AttackCode0
Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial TrainingCode0
Show:102550
← PrevPage 14 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