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 1101–1125 of 1746 papers

Title	Date	Tasks	Status	Hype
A Framework for Verification of Wasserstein Adversarial Robustness	Oct 13, 2021	Adversarial AttackAdversarial Robustness	—Unverified	0
Are models trained on temporally-continuous data streams more adversarially robust?	Oct 12, 2021	Adversarial Robustness	—Unverified	0
Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN	Oct 12, 2021	Adversarial RobustnessFoveation	—Unverified	0
Gated Information Bottleneck for Generalization in Sequential Environments	Oct 12, 2021	Adversarial RobustnessOut of Distribution (OOD) Detection	CodeCode Available	0
Parameterizing Activation Functions for Adversarial Robustness	Oct 11, 2021	Adversarial Robustness	—Unverified	0
Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuning	Oct 9, 2021	Adversarial RobustnessFace Recognition	—Unverified	0
Adversarial Robustness of Program Synthesis Models	Oct 8, 2021	Adversarial RobustnessProgram Synthesis	—Unverified	0
Observations on K-image Expansion of Image-Mixing Augmentation for Classification	Oct 8, 2021	Adversarial RobustnessClassification	CodeCode Available	0
Explainability-Aware One Point Attack for Point Cloud Neural Networks	Oct 8, 2021	3D Object RecognitionAdversarial Robustness	CodeCode Available	1
The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks	Oct 8, 2021	Adversarial RobustnessInductive Bias	CodeCode Available	1
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks	Oct 7, 2021	Adversarial Robustness	CodeCode Available	1
Improving Adversarial Robustness for Free with Snapshot Ensemble	Oct 7, 2021	Adversarial Robustness	—Unverified	0
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs	Oct 6, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Adversarial Robustness Verification and Attack Synthesis in Stochastic Systems	Oct 5, 2021	Adversarial Robustness	CodeCode Available	0
Does Adversarial Robustness Really Imply Backdoor Vulnerability?	Sep 29, 2021	Adversarial Robustness	—Unverified	0
Certified Adversarial Robustness Under the Bounded Support Set	Sep 29, 2021	Adversarial Robustness	—Unverified	0
Dissecting Local Properties of Adversarial Examples	Sep 29, 2021	Adversarial Robustness	—Unverified	0
k-Mixup Regularization for Deep Learning via Optimal Transport	Sep 29, 2021	Adversarial RobustnessDeep Learning	—Unverified	0
Use of small auxiliary networks and scarce data to improve the adversarial robustness of deep learning models	Sep 29, 2021	Adversarial Robustnessimage-classification	—Unverified	0
Biased Multi-Domain Adversarial Training	Sep 29, 2021	Adversarial Robustness	—Unverified	0
Empirical Study of the Decision Region and Robustness in Deep Neural Networks	Sep 29, 2021	Adversarial AttackAdversarial Robustness	—Unverified	0
Function-Space Variational Inference for Deep Bayesian Classification	Sep 29, 2021	Adversarial RobustnessClassification	—Unverified	0
Provably Robust Transfer	Sep 29, 2021	Adversarial RobustnessTransfer Learning	—Unverified	0
Delving into Feature Space: Improving Adversarial Robustness by Feature Spectral Regularization	Sep 29, 2021	Adversarial RobustnessAttribute	—Unverified	0
GARNET: A Spectral Approach to Robust and Scalable Graph Neural Networks	Sep 29, 2021	Adversarial RobustnessGraph Embedding	—Unverified	0

Show:10 25 50

← PrevPage 45 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