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 601–650 of 1808 papers

TitleStatusHype
Data-Driven Subsampling in the Presence of an Adversarial ActorCode0
Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy ProtectionCode0
Data-Driven Falsification of Cyber-Physical SystemsCode0
A Classification-Guided Approach for Adversarial Attacks against Neural Machine TranslationCode0
Adversarial Attacks on Large Language Models Using Regularized RelaxationCode0
DAmageNet: A Universal Adversarial DatasetCode0
FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMsCode0
Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensembleCode0
Imperceptible Face Forgery Attack via Adversarial Semantic MaskCode0
Delving into Transferable Adversarial Examples and Black-box AttacksCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
Foiling Explanations in Deep Neural NetworksCode0
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single ImageCode0
GenAttack: Practical Black-box Attacks with Gradient-Free OptimizationCode0
Curls & Whey: Boosting Black-Box Adversarial AttacksCode0
Detecting Adversarial Examples in Batches -- a geometrical approachCode0
Detecting Adversarial Perturbations in Multi-Task PerceptionCode0
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion ModelsCode0
An Empirical Investigation of Randomized Defenses against Adversarial AttacksCode0
Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networksCode0
Feature Space Perturbations Yield More Transferable Adversarial ExamplesCode0
Determining Sequence of Image Processing Technique (IPT) to Detect Adversarial AttacksCode0
Adversarial and Clean Data Are Not TwinsCode0
CT-GAT: Cross-Task Generative Adversarial Attack based on TransferabilityCode0
FDA: Feature Disruptive AttackCode0
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate GradientsCode0
Fast Inference of Removal-Based Node InfluenceCode0
Differentiable Adversarial Attacks for Marked Temporal Point ProcessesCode0
Cross-lingual Cross-temporal Summarization: Dataset, Models, EvaluationCode0
Adversarial Attacks on Gaussian Process BanditsCode0
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation TechniquesCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
2D-Malafide: Adversarial Attacks Against Face Deepfake Detection SystemsCode0
Angelic Patches for Improving Third-Party Object Detector PerformanceCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of ArtifactsCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Explainable Graph Neural Networks Under FireCode0
Adversarial Attacks on Deep Neural Networks for Time Series ClassificationCode0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality MetricsCode0
FireBERT: Hardening BERT-based classifiers against adversarial attackCode0
Disrupting Deep Uncertainty Estimation Without Harming AccuracyCode0
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial AttacksCode0
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust PredictionsCode0
Adversarial Attack and Defense on Graph Data: A SurveyCode0
Task-generalizable Adversarial Attack based on Perceptual MetricCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Controversial stimuli: pitting neural networks against each other as models of human recognitionCode0
Show:102550
← PrevPage 13 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