SOTAVerified

Adversarial Defense

Competitions with currently unpublished results:

Papers

Showing 301350 of 403 papers

TitleStatusHype
Cassandra: Detecting Trojaned Networks from Adversarial Perturbations0
Anomaly Detection in Unsupervised Surveillance Setting Using Ensemble of Multimodal Data with Adversarial Defense0
Defending against adversarial attacks on medical imaging AI system, classification or detection?Code0
Adversarial Defense by Latent Style Transformations0
Tricking Adversarial Attacks To Fail0
mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural NetworksCode0
Exploring the role of Input and Output Layers of a Deep Neural Network in Adversarial Defense0
Revisiting Role of Autoencoders in Adversarial Settings0
Encryption Inspired Adversarial Defense for Visual Classification0
Class-Aware Domain Adaptation for Improving Adversarial Robustness0
RAIN: A Simple Approach for Robust and Accurate Image Classification NetworksCode0
Adversarial Attacks and Defenses: An Interpretation Perspective0
SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen CamerasCode0
Physically Realizable Adversarial Examples for LiDAR Object Detection0
Certified Defense to Image Transformations via Randomized SmoothingCode0
PaRoT: A Practical Framework for Robust Deep Neural Network TrainingCode0
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking0
Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural NetworksCode0
Smoothed Inference for Adversarially-Trained ModelsCode0
Defensive Few-shot LearningCode0
GraphDefense: Towards Robust Graph Convolutional NetworksCode0
MadNet: Using a MAD Optimization for Defending Against Adversarial Attacks0
Adversarial Defense via Local Flatness Regularization0
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation0
A New Defense Against Adversarial Images: Turning a Weakness into a StrengthCode0
Adversarial Defense via Learning to Generate Diverse AttacksCode0
Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks0
Universal Learning Approach for Adversarial Defense0
Simple and Effective Stochastic Neural Networks0
Training Robust Deep Neural Networks via Adversarial Noise Propagation0
Natural Language Adversarial Defense through Synonym EncodingCode0
Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix0
White-Box Adversarial Defense via Self-Supervised Data EstimationCode0
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders0
Gated Convolutional Networks with Hybrid Connectivity for Image ClassificationCode0
Testing Robustness Against Unforeseen AdversariesCode0
Adversarial Defense by Suppressing High-frequency ComponentsCode0
Adversarial Robustness through Local Linearization0
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"0
Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization0
Improved Adversarial Robustness via Logit Regularization Methods0
Defending Against Universal Attacks Through Selective Feature RegenerationCode0
Robustness for Non-Parametric Classification: A Generic Attack and DefenseCode0
Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network RobustnessCode0
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and DefensesCode0
Scaleable input gradient regularization for adversarial robustnessCode0
Enhancing Adversarial Defense by k-Winners-Take-AllCode0
Privacy Risks of Securing Machine Learning Models against Adversarial ExamplesCode0
Adversarial Examples for Electrocardiograms0
Adversarial Defense Framework for Graph Neural Network0
Show:102550
← PrevPage 7 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1WRN-28-10Accuracy90.03Unverified
2Diffusion ClassifierAccuracy89.85Unverified
3Stochastic-LWTA/PGD/WideResNet-34-10Accuracy84.3Unverified
4Ours (Stochastic-LWTA/PGD/WideResNet-34-5)Accuracy83.4Unverified
5Ours (Stochastic-LWTA/PGD/WideResNet-34-1)Accuracy81.87Unverified
6ResNet18 (TRADES-ANCRA/PGD-40)Accuracy81.7Unverified
7Stochastic-LWTA/PGD/WideResNet-34-5Attack: AutoAttack81.22Unverified
8PCL (against PGD, white box)Accuracy46.7Unverified
#ModelMetricClaimedVerifiedStatus
1SAT-EfficientNet-L1Accuracy58.6Unverified
2LLR-ResNet-152Accuracy47Unverified
3ResNet-152 free-m=4Accuracy36Unverified
4ResNet-101 free-m=4Accuracy34.3Unverified
5ResNet-50 free-m=4Accuracy31.8Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet101Accuracy99.8Unverified
2InceptionV3Accuracy98.6Unverified
3Feature DenoisingAccuracy49.5Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-152 DenoiseAccuracy42.8Unverified
2ResNeXt-101 DenoiseAllAccuracy40.4Unverified
3ResNet-152Accuracy39Unverified
#ModelMetricClaimedVerifiedStatus
1Defense GANAccuracy0.85Unverified
2PuVAEAccuracy0.81Unverified
#ModelMetricClaimedVerifiedStatus
1Feature DenoisingAccuracy50.6Unverified
#ModelMetricClaimedVerifiedStatus
1Auto Encoder-Block Switching defense with GradCAMAccuracy 88.54Unverified