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 1401–1450 of 1808 papers

TitleStatusHype
Controversial stimuli: pitting neural networks against each other as models of human recognitionCode0
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMsCode0
Foiling Explanations in Deep Neural NetworksCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
Combining Generators of Adversarial Malware Examples to Increase Evasion RateCode0
ColorFool: Semantic Adversarial ColorizationCode0
Explainable Graph Neural Networks Under FireCode0
Explainable and Safe Reinforcement Learning for Autonomous Air MobilityCode0
Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan ScriptCode0
Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial ExamplesCode0
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single ImageCode0
PDPGD: Primal-Dual Proximal Gradient Descent Adversarial AttackCode0
VIP: Visual Information Protection through Adversarial Attacks on Vision-Language ModelsCode0
The UCR Time Series ArchiveCode0
Expanding Scope: Adapting English Adversarial Attacks to ChineseCode0
Excess Capacity and Backdoor PoisoningCode0
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent VariablesCode0
A principled approach for generating adversarial images under non-smooth dissimilarity metricsCode0
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation FrameworkCode0
Rob-GAN: Generator, Discriminator, and Adversarial AttackerCode0
Adversarial Examples on Graph Data: Deep Insights into Attack and DefenseCode0
From Flexibility to Manipulation: The Slippery Slope of XAI EvaluationCode0
Class-Conditioned Transformation for Enhanced Robust Image ClassificationCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based AttacksCode0
PermuteAttack: Counterfactual Explanation of Machine Learning Credit ScorecardsCode0
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial AttacksCode0
GenAttack: Practical Black-box Attacks with Gradient-Free OptimizationCode0
Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node ImplantationCode0
Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of ComponentsCode0
Evaluating the Validity of Word-level Adversarial Attacks with Large Language ModelsCode0
Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial TrainingCode0
Taking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer DomainCode0
Evaluating the Robustness of Adversarial Defenses in Malware Detection SystemsCode0
Generate synthetic samples from tabular dataCode0
Threatening Patch Attacks on Object Detection in Optical Remote Sensing ImagesCode0
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and DefenseCode0
Adversarial Attack and Defense for Non-Parametric Two-Sample TestsCode0
Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and AdverbsCode0
Generating Natural Adversarial ExamplesCode0
Generating Natural Language Adversarial Examples through Probability Weighted Word SaliencyCode0
Certified Defenses against Adversarial ExamplesCode0
A practical approach to evaluating the adversarial distance for machine learning classifiersCode0
Any Target Can be Offense: Adversarial Example Generation via Generalized Latent InfectionCode0
Generating Textual Adversaries with Minimal PerturbationCode0
Generating Unrestricted 3D Adversarial Point CloudsCode0
CAPAA: Classifier-Agnostic Projector-Based Adversarial AttackCode0
Adversarial attacks on neural networks through canonical Riemannian foliationsCode0
Show:102550
← PrevPage 29 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