Adversarial Robustness

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1401–1425 of 1746 papers

Title	Date	Tasks	Status	Hype
Affine-Invariant Robust Training	Oct 8, 2020	Adversarial RobustnessBIG-bench Machine Learning	—Unverified	0
Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination	Oct 8, 2020	Adversarial RobustnessMulti-Armed Bandits	—Unverified	0
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples	Oct 7, 2020	Adversarial Robustness	CodeCode Available	1
Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective	Oct 7, 2020	Adversarial Robustness	CodeCode Available	0
Constraining Logits by Bounded Function for Adversarial Robustness	Oct 6, 2020	Adversarial Robustness	—Unverified	0
Do Wider Neural Networks Really Help Adversarial Robustness?	Oct 3, 2020	Adversarial Robustness	—Unverified	0
Query complexity of adversarial attacks	Oct 2, 2020	Adversarial Robustness	—Unverified	0
Bag of Tricks for Adversarial Training	Oct 1, 2020	Adversarial RobustnessBenchmarking	CodeCode Available	1
On The Adversarial Robustness of 3D Point Cloud Classification	Sep 28, 2020	3D Point Cloud ClassificationAdversarial Robustness	—Unverified	0
Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness	Sep 28, 2020	Adversarial Robustness	—Unverified	0
Proper Measure for Adversarial Robustness	Sep 28, 2020	Adversarial Robustness	—Unverified	0
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients	Sep 28, 2020	Adversarial DefenseAdversarial Robustness	CodeCode Available	0
Differentially Private Adversarial Robustness Through Randomized Perturbations	Sep 27, 2020	Adversarial RobustnessSemantic Similarity	—Unverified	0
Adversarial robustness via stochastic regularization of neural activation sensitivity	Sep 23, 2020	Adversarial RobustnessSensitivity	—Unverified	0
Semantics-Preserving Adversarial Training	Sep 23, 2020	Adversarial Robustness	—Unverified	0
Feature Distillation With Guided Adversarial Contrastive Learning	Sep 21, 2020	Adversarial RobustnessContrastive Learning	—Unverified	0
Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness	Sep 21, 2020	Adversarial RobustnessDiversity	CodeCode Available	0
Adversarial Robustness through Bias Variance Decomposition: A New Perspective for Federated Learning	Sep 18, 2020	Adversarial RobustnessFederated Learning	—Unverified	0
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering	Sep 17, 2020	Adversarial RobustnessQuestion Answering	—Unverified	0
Large Norms of CNN Layers Do Not Hurt Adversarial Robustness	Sep 17, 2020	Adversarial Robustness	CodeCode Available	0
Label Smoothing and Adversarial Robustness	Sep 17, 2020	Adversarial AttackAdversarial Robustness	—Unverified	0
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup	Sep 15, 2020	Adversarial RobustnessImage Classification	CodeCode Available	1
Robust Deep Learning Ensemble against Deception	Sep 14, 2020	Adversarial RobustnessDeep Learning	—Unverified	0
Defending Against Multiple and Unforeseen Adversarial Videos	Sep 11, 2020	Adversarial RobustnessGeneral Classification	—Unverified	0
Achieving Adversarial Robustness via Sparsity	Sep 11, 2020	Adversarial RobustnessNetwork Pruning	—Unverified	0

Show:10 25 50

← PrevPage 57 of 70Next →

All datasets AdvGLUE CIFAR-10 ImageNet ImageNet-A ImageNet-C Stylized ImageNet CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DeBERTa (single model)	Accuracy	0.61	—	Unverified
2	ALBERT (single model)	Accuracy	0.59	—	Unverified
3	T5 (single model)	Accuracy	0.57	—	Unverified
4	SMART_RoBERTa (single model)	Accuracy	0.54	—	Unverified
5	FreeLB (single model)	Accuracy	0.5	—	Unverified
6	RoBERTa (single model)	Accuracy	0.5	—	Unverified
7	InfoBERT (single model)	Accuracy	0.46	—	Unverified
8	ELECTRA (single model)	Accuracy	0.42	—	Unverified
9	BERT (single model)	Accuracy	0.34	—	Unverified
10	SMART_BERT (single model)	Accuracy	0.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed classifier	Accuracy	95.23	—	Unverified
2	Stochastic-LWTA/PGD/WideResNet-34-10	Accuracy	92.26	—	Unverified
3	Stochastic-LWTA/PGD/WideResNet-34-5	Accuracy	91.88	—	Unverified
4	GLOT-DR	Accuracy	84.13	—	Unverified
5	TRADES-ANCRA/ResNet18	Accuracy	81.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (SGD, Cosine)	Accuracy	77.4	—	Unverified
2	ResNet-50 (SGD, Step)	Accuracy	76.9	—	Unverified
3	DeiT-S (AdamW, Cosine)	Accuracy	76.8	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	76.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	12.2	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	3.3	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	3.2	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	3.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (AdamW, Cosine)	mean Corruption Error (mCE)	59.3	—	Unverified
2	ResNet-50 (SGD, Step)	mean Corruption Error (mCE)	57.9	—	Unverified
3	ResNet-50 (SGD, Cosine)	mean Corruption Error (mCE)	56.9	—	Unverified
4	DeiT-S (AdamW, Cosine)	mean Corruption Error (mCE)	48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	13	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	8.4	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	8.3	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	8.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed Classifier	Clean Accuracy	85.21	—	Unverified
2	ResNet18/MART-ANCRA	Clean Accuracy	60.1	—	Unverified