Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 301–325 of 403 papers

Title	Date	Tasks	Status	Hype
SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras	Apr 4, 2020	Adversarial AttackAdversarial Defense	CodeCode Available	0
Physically Realizable Adversarial Examples for LiDAR Object Detection	Apr 1, 2020	Adversarial DefenseAutonomous Driving	—Unverified	0
Toward Adversarial Robustness via Semi-supervised Robust Training	Mar 16, 2020	Adversarial DefenseAdversarial Robustness	CodeCode Available	1
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness	Mar 2, 2020	Adversarial DefenseAdversarial Robustness	CodeCode Available	1
Certified Defense to Image Transformations via Randomized Smoothing	Feb 27, 2020	Adversarial DefenseProvable Adversarial Defense	CodeCode Available	0
PaRoT: A Practical Framework for Robust Deep Neural Network Training	Jan 7, 2020	Adversarial DefenseAutonomous Vehicles	CodeCode Available	0
ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense	Jan 2, 2020	Adversarial DefenseDenoising	CodeCode Available	1
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking	Dec 16, 2019	Adversarial DefenseAnomaly Detection	—Unverified	0
Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks	Dec 1, 2019	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
Smoothed Inference for Adversarially-Trained Models	Nov 17, 2019	Adversarial Defense	CodeCode Available	0
Defensive Few-shot Learning	Nov 16, 2019	Adversarial DefenseFew-Shot Learning	CodeCode Available	0
GraphDefense: Towards Robust Graph Convolutional Networks	Nov 11, 2019	Adversarial Defense	CodeCode Available	0
MadNet: Using a MAD Optimization for Defending Against Adversarial Attacks	Nov 3, 2019	Adversarial DefenseAdversarial Robustness	—Unverified	0
Adversarial Defense via Local Flatness Regularization	Oct 27, 2019	Adversarial Defense	—Unverified	0
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation	Oct 17, 2019	Adversarial DefenseImage Generation	—Unverified	0
A New Defense Against Adversarial Images: Turning a Weakness into a Strength	Oct 16, 2019	Adversarial Defense	CodeCode Available	0
Adversarial Defense via Learning to Generate Diverse Attacks	Oct 1, 2019	Adversarial Defense	CodeCode Available	0
Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks	Sep 25, 2019	Adversarial DefenseAudio Classification	—Unverified	0
Universal Learning Approach for Adversarial Defense	Sep 25, 2019	Adversarial Defense	—Unverified	0
Simple and Effective Stochastic Neural Networks	Sep 25, 2019	Adversarial AttackAdversarial Defense	—Unverified	0
Training Robust Deep Neural Networks via Adversarial Noise Propagation	Sep 19, 2019	Adversarial DefenseAdversarial Robustness	—Unverified	0
Natural Language Adversarial Defense through Synonym Encoding	Sep 15, 2019	Adversarial AttackAdversarial Defense	CodeCode Available	0
Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix	Sep 13, 2019	Adversarial DefenseTraffic Sign Recognition	—Unverified	0
White-Box Adversarial Defense via Self-Supervised Data Estimation	Sep 13, 2019	Adversarial DefenseSelf-Supervised Learning	CodeCode Available	0
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders	Sep 12, 2019	Adversarial DefenseAdversarial Robustness	—Unverified	0

Show:10 25 50

← PrevPage 13 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