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 251–275 of 1746 papers

Title	Date	Tasks	Status	Hype
Adversarial Robustness against Multiple and Single l_p-Threat Models via Quick Fine-Tuning of Robust Classifiers	May 26, 2021	Adversarial Robustness	CodeCode Available	1
Adversarial Attacks on Graph Classification via Bayesian Optimisation	Nov 4, 2021	Adversarial RobustnessBayesian Optimisation	CodeCode Available	1
Adversarial Robustness Against the Union of Multiple Perturbation Models	Sep 9, 2019	Adversarial Robustness	CodeCode Available	1
SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher	Nov 17, 2020	Adversarial Robustness	CodeCode Available	1
(Certified!!) Adversarial Robustness for Free!	Jun 21, 2022	Adversarial RobustnessDenoising	CodeCode Available	1
Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal	Dec 7, 2021	Adversarial RobustnessSensitivity	CodeCode Available	1
Adversarial Attacks on Graph Classifiers via Bayesian Optimisation	Dec 1, 2021	Adversarial RobustnessBayesian Optimisation	CodeCode Available	1
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization	Apr 11, 2024	Adversarial Robustness	CodeCode Available	1
Adversarial Robustness as a Prior for Learned Representations	Jun 3, 2019	Adversarial Robustness	CodeCode Available	1
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?	Aug 16, 2024	Adversarial Robustness	CodeCode Available	1
A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion	Mar 29, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available	1
CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models	Jun 9, 2022	Adversarial DefenseAdversarial Robustness	CodeCode Available	1
ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection	Mar 12, 2020	Adversarial RobustnessNovelty Detection	CodeCode Available	1
Certified Adversarial Robustness via Randomized Smoothing	Feb 8, 2019	Adversarial DefenseAdversarial Robustness	CodeCode Available	1
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning	May 1, 2022	Adversarial Robustnesstext-classification	CodeCode Available	1
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection	Feb 10, 2021	Adversarial Robustnessfeature selection	CodeCode Available	1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs	Oct 6, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks	Oct 10, 2023	Adversarial Robustness	CodeCode Available	1
Adversarial Attacks on ML Defense Models Competition	Oct 15, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Consistency Regularization for Adversarial Robustness	Mar 8, 2021	Adversarial RobustnessData Augmentation	CodeCode Available	1
Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation	Jun 28, 2023	Adversarial RobustnessKnowledge Distillation	CodeCode Available	1
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks	May 19, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Adversarial Robustness for Code	Feb 11, 2020	Adversarial RobustnessBIG-bench Machine Learning	CodeCode Available	1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness	Jul 22, 2022	Adversarial RobustnessContrastive Learning	CodeCode Available	1
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness	Dec 5, 2021	Adversarial AttackAdversarial Defense	CodeCode Available	1

Show:10 25 50

← PrevPage 11 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