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

Showing 151175 of 1808 papers

TitleStatusHype
Adversarial Training for Free!Code1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
Adversarial Attack and Defense in Deep RankingCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
Adversarial Attack and Defense of Structured Prediction ModelsCode1
Black-box Adversarial Example Generation with Normalizing FlowsCode1
Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving ScenariosCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Certifying LLM Safety against Adversarial PromptingCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
Adversarial Attack and Defense Strategies for Deep Speaker Recognition SystemsCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
Contextualized Perturbation for Textual Adversarial AttackCode1
Adversarial Examples for Semantic Segmentation and Object DetectionCode1
3D Gaussian Splat VulnerabilitiesCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Alleviating Adversarial Attacks on Variational Autoencoders with MCMCCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless NetworksCode1
Adversarial Learning for Robust Deep ClusteringCode1
Show:102550
← PrevPage 7 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified