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 1076–1100 of 1746 papers

Title	Date	Tasks	Status	Hype
Characterizing the adversarial vulnerability of speech self-supervised learning	Nov 8, 2021	Adversarial RobustnessBenchmarking	—Unverified	0
Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning	Nov 8, 2021	Adversarial RobustnessBenchmarking	CodeCode Available	1
A Unified Game-Theoretic Interpretation of Adversarial Robustness	Nov 5, 2021	Adversarial Robustness	CodeCode Available	1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models	Nov 4, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Adversarial Attacks on Graph Classification via Bayesian Optimisation	Nov 4, 2021	Adversarial RobustnessBayesian Optimisation	CodeCode Available	1
Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness	Nov 3, 2021	Adversarial RobustnessSensitivity	—Unverified	0
HypMix: Hyperbolic Interpolative Data Augmentation	Nov 1, 2021	Adversarial RobustnessData Augmentation	CodeCode Available	1
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding	Nov 1, 2021	Adversarial RobustnessAll	—Unverified	0
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?	Nov 1, 2021	Adversarial RobustnessContrastive Learning	CodeCode Available	1
Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach	Oct 30, 2021	Adversarial Robustness	CodeCode Available	0
Adversarial Robustness with Semi-Infinite Constrained Learning	Oct 29, 2021	Adversarial Robustness	—Unverified	0
Holistic Deep Learning	Oct 29, 2021	Adversarial RobustnessDeep Learning	CodeCode Available	1
Towards Evaluating the Robustness of Neural Networks Learned by Transduction	Oct 27, 2021	Adversarial RobustnessBilevel Optimization	CodeCode Available	0
Binarized ResNet: Enabling Robust Automatic Modulation Classification at the resource-constrained Edge	Oct 27, 2021	Adversarial RobustnessBinarization	—Unverified	0
A Frequency Perspective of Adversarial Robustness	Oct 26, 2021	Adversarial Robustness	—Unverified	0
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks	Oct 26, 2021	Adversarial Robustness	CodeCode Available	1
Adversarial Robustness in Multi-Task Learning: Promises and Illusions	Oct 26, 2021	Adversarial RobustnessMulti-Task Learning	CodeCode Available	0
How and When Adversarial Robustness Transfers in Knowledge Distillation?	Oct 22, 2021	Adversarial RobustnessKnowledge Distillation	—Unverified	0
Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff	Oct 22, 2021	Adversarial RobustnessBinary Classification	—Unverified	0
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness	Oct 21, 2021	Adversarial RobustnessCombinatorial Optimization	—Unverified	0
A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification	Oct 19, 2021	Adversarial RobustnessClassification	CodeCode Available	1
Improving Robustness using Generated Data	Oct 18, 2021	Adversarial Robustness	CodeCode Available	1
On the Sensitivity and Stability of Model Interpretations	Oct 16, 2021	Adversarial RobustnessDependency Parsing	—Unverified	0
Adversarial Attacks on ML Defense Models Competition	Oct 15, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness	Oct 13, 2021	Adversarial Robustness	—Unverified	0

Show:10 25 50

← PrevPage 44 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