Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 326–350 of 403 papers

Title	Date	Tasks	Status
Adversarial Defense via Learning to Generate Diverse Attacks	Oct 1, 2019	Adversarial Defense	CodeCode Available
Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks	Sep 25, 2019	Adversarial DefenseAudio Classification	—Unverified
Universal Learning Approach for Adversarial Defense	Sep 25, 2019	Adversarial Defense	—Unverified
Simple and Effective Stochastic Neural Networks	Sep 25, 2019	Adversarial AttackAdversarial Defense	—Unverified
Training Robust Deep Neural Networks via Adversarial Noise Propagation	Sep 19, 2019	Adversarial DefenseAdversarial Robustness	—Unverified
Natural Language Adversarial Defense through Synonym Encoding	Sep 15, 2019	Adversarial AttackAdversarial Defense	CodeCode Available
Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix	Sep 13, 2019	Adversarial DefenseTraffic Sign Recognition	—Unverified
White-Box Adversarial Defense via Self-Supervised Data Estimation	Sep 13, 2019	Adversarial DefenseSelf-Supervised Learning	CodeCode Available
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders	Sep 12, 2019	Adversarial DefenseAdversarial Robustness	—Unverified
Gated Convolutional Networks with Hybrid Connectivity for Image Classification	Aug 26, 2019	Adversarial DefenseClassification	CodeCode Available
Testing Robustness Against Unforeseen Adversaries	Aug 21, 2019	Adversarial DefenseAdversarial Robustness	CodeCode Available
Adversarial Defense by Suppressing High-frequency Components	Aug 19, 2019	Adversarial DefenseClassification	CodeCode Available
Adversarial Robustness through Local Linearization	Jul 4, 2019	Adversarial DefenseAdversarial Robustness	—Unverified
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"	Jul 1, 2019	Adversarial AttackAdversarial Defense	—Unverified
Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization	Jun 25, 2019	Adversarial DefenseImage Segmentation	—Unverified
Improved Adversarial Robustness via Logit Regularization Methods	Jun 10, 2019	Adversarial DefenseAdversarial Robustness	—Unverified
Defending Against Universal Attacks Through Selective Feature Regeneration	Jun 8, 2019	Adversarial Defense	CodeCode Available
Robustness for Non-Parametric Classification: A Generic Attack and Defense	Jun 7, 2019	Adversarial AttackAdversarial Defense	CodeCode Available
Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness	Jun 7, 2019	Adversarial DefenseFraud Detection	CodeCode Available
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses	Jun 1, 2019	Adversarial AttackAdversarial Defense	CodeCode Available
Scaleable input gradient regularization for adversarial robustness	May 27, 2019	Adversarial AttackAdversarial Defense	CodeCode Available
Enhancing Adversarial Defense by k-Winners-Take-All	May 25, 2019	Adversarial DefenseAll	CodeCode Available
Privacy Risks of Securing Machine Learning Models against Adversarial Examples	May 24, 2019	Adversarial DefenseBIG-bench Machine Learning	CodeCode Available
Adversarial Examples for Electrocardiograms	May 13, 2019	Adversarial DefenseArrhythmia Detection	—Unverified
Adversarial Defense Framework for Graph Neural Network	May 9, 2019	Adversarial DefenseContrastive Learning	—Unverified

Show:10 25 50

← PrevPage 14 of 17Next →

All datasets CIFAR-10 ImageNet (non-targeted PGD, max perturbation=4)ImageNet ImageNet (targeted PGD, max perturbation=16)MNIST CAAD 2018 miniImageNet

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	WRN-28-10	Accuracy	90.03	—	Unverified
2	Diffusion Classifier	Accuracy	89.85	—	Unverified
3	Stochastic-LWTA/PGD/WideResNet-34-10	Accuracy	84.3	—	Unverified
4	Ours (Stochastic-LWTA/PGD/WideResNet-34-5)	Accuracy	83.4	—	Unverified
5	Ours (Stochastic-LWTA/PGD/WideResNet-34-1)	Accuracy	81.87	—	Unverified
6	ResNet18 (TRADES-ANCRA/PGD-40)	Accuracy	81.7	—	Unverified
7	Stochastic-LWTA/PGD/WideResNet-34-5	Attack: AutoAttack	81.22	—	Unverified
8	PCL (against PGD, white box)	Accuracy	46.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SAT-EfficientNet-L1	Accuracy	58.6	—	Unverified
2	LLR-ResNet-152	Accuracy	47	—	Unverified
3	ResNet-152 free-m=4	Accuracy	36	—	Unverified
4	ResNet-101 free-m=4	Accuracy	34.3	—	Unverified
5	ResNet-50 free-m=4	Accuracy	31.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet101	Accuracy	99.8	—	Unverified
2	InceptionV3	Accuracy	98.6	—	Unverified
3	Feature Denoising	Accuracy	49.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-152 Denoise	Accuracy	42.8	—	Unverified
2	ResNeXt-101 DenoiseAll	Accuracy	40.4	—	Unverified
3	ResNet-152	Accuracy	39	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Defense GAN	Accuracy	0.85	—	Unverified
2	PuVAE	Accuracy	0.81	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Feature Denoising	Accuracy	50.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Auto Encoder-Block Switching defense with GradCAM	Accuracy	88.54	—	Unverified