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 801–850 of 1808 papers

TitleStatusHype
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation RobustnessCode1
Rethinking Textual Adversarial Defense for Pre-trained Language Models—0
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks—0
Defending Substitution-Based Profile Pollution Attacks on Sequential RecommendersCode0
Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense MechanismsCode5
Decorrelative Network Architecture for Robust Electrocardiogram ClassificationCode0
Prior-Guided Adversarial Initialization for Fast Adversarial TrainingCode1
Multi-step domain adaptation by adversarial attack to H ΔH-divergence—0
DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking—0
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Adversarial Examples for Model-Based Control: A Sensitivity Analysis—0
Perturbation Inactivation Based Adversarial Defense for Face RecognitionCode1
Frequency Domain Model Augmentation for Adversarial AttackCode1
How many perturbations break this model? Evaluating robustness beyond adversarial accuracyCode0
On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network—0
Query-Efficient Adversarial Attack Based on Latin Hypercube SamplingCode0
Learning to Accelerate Approximate Methods for Solving Integer Programming via Early FixingCode0
RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries—0
Resilience of Named Entity Recognition Models under Adversarial AttackCode0
ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations—0
SHARP: Search-Based Adversarial Attack for Structured Prediction—0
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Robustness of Explanation Methods for NLP Models—0
Adversarial Zoom Lens: A Novel Physical-World Attack to DNNs—0
A Framework for Understanding Model Extraction Attack and Defense—0
AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture—0
SSMI: How to Make Objects of Interest Disappear without Accessing Object Detectors?—0
Towards Adversarial Attack on Vision-Language Pre-training ModelsCode1
Detecting Adversarial Examples in Batches -- a geometrical approachCode0
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Proximal Splitting Adversarial Attacks for Semantic SegmentationCode1
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective—0
Adversarial Vulnerability of Randomized EnsemblesCode1
Darknet Traffic Classification and Adversarial Attacks—0
AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems—0
Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning—0
Saliency Attack: Towards Imperceptible Black-box Adversarial AttackCode0
Adversarial RAW: Image-Scaling Attack Against Imaging Pipeline—0
Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNsCode0
Attack-Agnostic Adversarial Detection—0
On the Perils of Cascading Robust ClassifiersCode0
On the reversibility of adversarial attacks—0
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural NetworksCode1
Semantic Autoencoder and Its Potential Usage for Adversarial Attack—0
Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models—0
Mixture GAN For Modulation Classification Resiliency Against Adversarial Attacks—0
On the Robustness of Safe Reinforcement Learning under Observational PerturbationsCode1
Superclass Adversarial Attack—0
Unfooling Perturbation-Based Post Hoc ExplainersCode0
Physical-World Optical Adversarial Attacks on 3D Face Recognition—0
Show:102550
← PrevPage 17 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