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 1701–1725 of 1746 papers

Title	Date	Tasks	Status	Hype
Sorting out Lipschitz function approximation	Nov 13, 2018	Adversarial RobustnessGeneralization Bounds	CodeCode Available	0
Theoretical Analysis of Adversarial Learning: A Minimax Approach	Nov 13, 2018	Adversarial RobustnessGeneral Classification	—Unverified	0
New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling	Nov 8, 2018	Adversarial Robustness	—Unverified	0
Improving Adversarial Robustness by Encouraging Discriminative Features	Nov 1, 2018	Adversarial Robustness	—Unverified	0
On the Effectiveness of Minimal Context Selection for Robust Question Answering	Oct 30, 2018	Adversarial RobustnessQuestion Answering	—Unverified	0
Logit Pairing Methods Can Fool Gradient-Based Attacks	Oct 29, 2018	Adversarial Robustness	CodeCode Available	0
Towards Robust Deep Neural Networks	Oct 27, 2018	Adversarial RobustnessComputational chemistry	—Unverified	0
Improving Document Binarization via Adversarial Noise-Texture Augmentation	Oct 25, 2018	Adversarial RobustnessBinarization	CodeCode Available	0
Evading classifiers in discrete domains with provable optimality guarantees	Oct 25, 2018	Adversarial RobustnessSpam detection	CodeCode Available	0
Sparse DNNs with Improved Adversarial Robustness	Oct 23, 2018	Adversarial RobustnessGeneral Classification	—Unverified	0
Average Margin Regularization for Classifiers	Oct 9, 2018	Adversarial Robustness	—Unverified	0
Generalized No Free Lunch Theorem for Adversarial Robustness	Oct 8, 2018	Adversarial Robustness	—Unverified	0
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness	Oct 4, 2018	Adversarial RobustnessDenoising	—Unverified	0
Improved robustness to adversarial examples using Lipschitz regularization of the loss	Oct 1, 2018	Adversarial Robustness	CodeCode Available	0
Knowledge-guided Semantic Computing Network	Sep 29, 2018	Adversarial RobustnessObject Recognition	—Unverified	0
Interpreting Adversarial Robustness: A View from Decision Surface in Input Space	Sep 29, 2018	Adversarial Robustness	—Unverified	0
CAAD 2018: Generating Transferable Adversarial Examples	Sep 29, 2018	Adversarial AttackAdversarial Defense	CodeCode Available	0
Distilled Agent DQN for Provable Adversarial Robustness	Sep 27, 2018	Adversarial Robustnessreinforcement-learning	—Unverified	0
Certified Adversarial Robustness with Additive Noise	Sep 10, 2018	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability	Sep 9, 2018	Adversarial Robustness	CodeCode Available	0
Lipschitz regularized Deep Neural Networks generalize and are adversarially robust	Aug 28, 2018	Adversarial Robustness	—Unverified	0
Implicit Generative Modeling of Random Noise during Training for Adversarial Robustness	Jul 5, 2018	Adversarial Robustness	CodeCode Available	0
Adversarial Robustness Toolbox v1.0.0	Jul 3, 2018	Adversarial RobustnessBIG-bench Machine Learning	CodeCode Available	3
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks	Jun 5, 2018	Adversarial AttackAdversarial Robustness	—Unverified	0
AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks	May 30, 2018	Adversarial Robustness	CodeCode Available	0

Show:10 25 50

← PrevPage 69 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