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 1326–1350 of 1746 papers

Title	Date	Tasks	Status
Robust Certification for Laplace Learning on Geometric Graphs	Apr 22, 2021	Adversarial AttackAdversarial Robustness	—Unverified
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting	Apr 22, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available
Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations	Apr 21, 2021	Adversarial RobustnessDenoising	—Unverified
Removing Adversarial Noise in Class Activation Feature Space	Apr 19, 2021	Adversarial RobustnessDenoising	—Unverified
Calibration and Consistency of Adversarial Surrogate Losses	Apr 19, 2021	Adversarial Robustness	—Unverified
On the Sensitivity and Stability of Model Interpretations in NLP	Apr 18, 2021	Adversarial RobustnessDependency Parsing	CodeCode Available
Does language help generalization in vision models?	Apr 16, 2021	Adversarial RobustnessClustering	CodeCode Available
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition	Apr 14, 2021	Adversarial RobustnessGPU	—Unverified
Relating Adversarially Robust Generalization to Flat Minima	Apr 9, 2021	Adversarial Robustness	—Unverified
Adversarial Robustness Guarantees for Gaussian Processes	Apr 7, 2021	Adversarial RobustnessGaussian Processes	CodeCode Available
Universal Adversarial Training with Class-Wise Perturbations	Apr 7, 2021	Adversarial Robustness	—Unverified
Robust Adversarial Classification via Abstaining	Apr 6, 2021	Adversarial RobustnessBinary Classification	—Unverified
Adversarial Attacks and Defenses for Speech Recognition Systems	Mar 31, 2021	Adversarial RobustnessAutomatic Speech Recognition	—Unverified
Class-Aware Robust Adversarial Training for Object Detection	Mar 30, 2021	Adversarial RobustnessObject	—Unverified
Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness	Mar 30, 2021	Adversarial RobustnessImitation Learning	—Unverified
Towards Understanding Adversarial Robustness of Optical Flow Networks	Mar 30, 2021	Adversarial RobustnessOptical Flow Estimation	CodeCode Available
Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness	Mar 27, 2021	Adversarial Robustness	—Unverified
Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy	Mar 15, 2021	Adversarial Robustness	CodeCode Available
Reframing Neural Networks: Deep Structure in Overcomplete Representations	Mar 10, 2021	Adversarial RobustnessModel Selection	—Unverified
Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN	Mar 8, 2021	Adversarial DefenseAdversarial Robustness	—Unverified
Constrained Learning with Non-Convex Losses	Mar 8, 2021	Adversarial RobustnessFairness	—Unverified
Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations	Mar 8, 2021	Adversarial Robustness	—Unverified
Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks	Mar 4, 2021	Adversarial RobustnessLow-Rank Matrix Completion	—Unverified
Shift Invariance Can Reduce Adversarial Robustness	Mar 3, 2021	Adversarial Robustness	CodeCode Available
Smoothness Analysis of Adversarial Training	Mar 2, 2021	Adversarial Robustness	—Unverified

Show:10 25 50

← PrevPage 54 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