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 101–150 of 1808 papers

TitleStatusHype
Adversarial Attack on Large Scale GraphCode1
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical FlowCode1
Adversarial Training for Free!Code1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating DeepfakesCode1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
Contextualized Perturbation for Textual Adversarial AttackCode1
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution LearningCode1
Boosting Adversarial Transferability via Gradient Relevance AttackCode1
Black-box Adversarial Example Generation with Normalizing FlowsCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
A Survey On Universal Adversarial AttackCode1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial AttackCode1
Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object TrackingCode1
Frequency Domain Adversarial Training for Robust Volumetric Medical SegmentationCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
BayesOpt Adversarial AttackCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
R&R: Metric-guided Adversarial Sentence GenerationCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake DetectionCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
Adversarial Immunization for Certifiable Robustness on GraphsCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Adversarial Learning for Robust Deep ClusteringCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
BERT-ATTACK: Adversarial Attack Against BERT Using BERTCode1
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness VerificationCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
3D Adversarial Attacks Beyond Point CloudCode1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNsCode1
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning ModelsCode1
Adversarial Ranking Attack and DefenseCode1
Fooling the Image Dehazing Models by First Order GradientCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
Certifying LLM Safety against Adversarial PromptingCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsCode1
Show:102550
← PrevPage 3 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