Adversarial Defense

Competitions with currently unpublished results:

TrojAI

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–75 of 403 papers

Title	Date	Tasks	Status	Hype
Deep Adversarial Defense Against Multilevel-Lp Attacks	Jul 12, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Shedding More Light on Robust Classifiers under the lens of Energy-based Models	Jul 8, 2024	Adversarial Defense	CodeCode Available	0
L_p-norm Distortion-Efficient Adversarial Attack	Jul 3, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising	Jun 28, 2024	Adversarial DefenseDenoising	CodeCode Available	0
Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors	Jun 21, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning	Jun 19, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification	Jun 18, 2024	Adversarial DefenseDenoising	CodeCode Available	0
Improving Adversarial Robustness via Decoupled Visual Representation Masking	Jun 16, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models	Jun 13, 2024	Adversarial Defenseimage-classification	—Unverified	0
Adversarial Evasion Attack Efficiency against Large Language Models	Jun 12, 2024	Adversarial DefenseClassification	—Unverified	0
Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs	Jun 6, 2024	Adversarial DefenseGraph Neural Network	—Unverified	0
Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships	May 29, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks	May 28, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
Large Language Model Sentinel: LLM Agent for Adversarial Purification	May 24, 2024	Adversarial DefenseAdversarial Purification	—Unverified	0
Robust width: A lightweight and certifiable adversarial defense	May 24, 2024	Adversarial Defensecompressed sensing	CodeCode Available	0
Adaptive Batch Normalization Networks for Adversarial Robustness	May 20, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks	May 14, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective	Apr 30, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment	Apr 30, 2024	Adversarial DefenseImage Quality Assessment	—Unverified	0
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation	Apr 19, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models	Apr 16, 2024	Adversarial DefenseAdversarial Robustness	CodeCode Available	1
Struggle with Adversarial Defense? Try Diffusion	Apr 12, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	Apr 4, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Adversarial Attacks and Dimensionality in Text Classifiers	Apr 3, 2024	Adversarial AttackAdversarial Defense	—Unverified	0
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay	Apr 2, 2024	Adversarial Defense	—Unverified	0

Show:10 25 50

← PrevPage 3 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