Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 403 papers

Title	Date	Tasks	Status	Hype
Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models	Mar 25, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals	Mar 24, 2024	Adversarial Defense	—Unverified	0
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions	Mar 23, 2024	Adversarial Defenseobject-detection	—Unverified	0
ADAPT to Robustify Prompt Tuning Vision Transformers	Mar 19, 2024	Adversarial Defense	CodeCode Available	0
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM	Mar 18, 2024	Adversarial AttackAdversarial Defense	CodeCode Available	0
Revisiting Adversarial Training under Long-Tailed Distributions	Mar 15, 2024	Adversarial DefenseData Augmentation	CodeCode Available	2
Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors	Mar 6, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense	Feb 29, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks	Feb 28, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
MGE: A Training-Free and Efficient Model Generation and Enhancement Scheme	Feb 27, 2024	Adversarial Defense	—Unverified	0
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off	Feb 22, 2024	Adversarial DefenseKnowledge Distillation	—Unverified	0
A Simple and Yet Fairly Effective Defense for Graph Neural Networks	Feb 21, 2024	Adversarial DefenseNode Classification	CodeCode Available	0
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models	Feb 19, 2024	Adversarial DefenseMultimodal Deep Learning	CodeCode Available	2
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness	Feb 2, 2024	Adversarial DefenseGraph Learning	—Unverified	0
Fast Adversarial Training against Textual Adversarial Attacks	Jan 23, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles	Dec 31, 2023	Adversarial AttackAdversarial Defense	—Unverified	0
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World	Dec 21, 2023	Adversarial DefenseNeural Network Security	—Unverified	0
Continual Adversarial Defense	Dec 15, 2023	Adversarial DefenseContinual Learning	CodeCode Available	0
Detection and Defense of Unlearnable Examples	Dec 14, 2023	Adversarial DefensePrivacy Preserving	CodeCode Available	0
Robust MRI Reconstruction by Smoothed Unrolling (SMUG)	Dec 12, 2023	Adversarial Defenseimage-classification	CodeCode Available	0
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval	Dec 12, 2023	Adversarial DefenseImage Retrieval	CodeCode Available	1
Defense Against Adversarial Attacks using Convolutional Auto-Encoders	Dec 6, 2023	Adversarial Defense	CodeCode Available	0
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model	Nov 28, 2023	Adversarial Defenseimage-classification	—Unverified	0
Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization	Oct 19, 2023	Adversarial Defense	CodeCode Available	0
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing	Oct 12, 2023	Adversarial Defense	CodeCode Available	0

Show:10 25 50

← PrevPage 4 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