Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–125 of 403 papers

Title	Date	Tasks	Status
Adversarial Robustness through Local Linearization	Jul 4, 2019	Adversarial DefenseAdversarial Robustness	—Unverified
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation	Oct 17, 2019	Adversarial DefenseImage Generation	—Unverified
OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack	Aug 1, 2024	Adversarial AttackAdversarial Defense	—Unverified
Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment	Apr 30, 2024	Adversarial DefenseImage Quality Assessment	—Unverified
Encryption Inspired Adversarial Defense for Visual Classification	May 16, 2020	Adversarial DefenseClassification	—Unverified
Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers	Sep 5, 2024	Adversarial DefenseLanguage Modelling	—Unverified
Adversarial Defense by Latent Style Transformations	Jun 17, 2020	Adversarial Defense	—Unverified
Certified Causal Defense with Generalizable Robustness	Aug 28, 2024	Adversarial Defense	—Unverified
Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization	Jun 25, 2019	Adversarial DefenseImage Segmentation	—Unverified
Evaluating Deception Detection Model Robustness To Linguistic Variation	Apr 23, 2021	Adversarial DefenseDeception Detection	—Unverified
Adversarial Masked Autoencoder Purifier with Defense Transferability	Jan 28, 2025	Adversarial DefenseAdversarial Robustness	—Unverified
Class-Aware Domain Adaptation for Improving Adversarial Robustness	May 10, 2020	Adversarial AttackAdversarial Defense	—Unverified
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features	Feb 23, 2025	Adversarial Defensebackdoor defense	—Unverified
Class-Disentanglement and Applications in Adversarial Detection and Defense	Dec 1, 2021	Adversarial DefenseDisentanglement	—Unverified
Efficient Two-Step Adversarial Defense for Deep Neural Networks	Oct 8, 2018	Adversarial DefenseVocal Bursts Valence Prediction	—Unverified
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense	Feb 29, 2024	Adversarial DefenseAdversarial Robustness	—Unverified
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"	Jul 1, 2019	Adversarial AttackAdversarial Defense	—Unverified
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning	Jun 1, 2021	Adversarial DefenseAdversarial Robustness	—Unverified
A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment	May 27, 2025	Adversarial AttackAdversarial Defense	—Unverified
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation	Dec 2, 2020	Adversarial DefenseSemantic Segmentation	—Unverified
Adversarial defense for deep speaker recognition using hybrid adversarial training	Oct 30, 2020	Adversarial DefenseSpeaker Recognition	—Unverified
Customizing an Adversarial Example Generator with Class-Conditional GANs	Jun 27, 2018	Adversarial DefenseDiversity	—Unverified
FaceGuard: A Self-Supervised Defense Against Adversarial Face Images	Nov 28, 2020	Adversarial AttackAdversarial Defense	—Unverified
AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense	Jul 14, 2021	Adversarial Defense	—Unverified
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning	Jun 19, 2024	Adversarial AttackAdversarial Defense	—Unverified

Show:10 25 50

← PrevPage 5 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