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 1026–1050 of 1746 papers

Title	Date	Tasks	Status
Fair Robust Active Learning by Joint Inconsistency	Sep 22, 2022	Active LearningAdversarial Attack	—Unverified
Audit and Improve Robustness of Private Neural Networks on Encrypted Data	Sep 20, 2022	Adversarial RobustnessPrivacy Preserving	—Unverified
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction	Sep 19, 2022	Adversarial AttackAdversarial Robustness	—Unverified
Towards Bridging the Performance Gaps of Joint Energy-based Models	Sep 16, 2022	Adversarial RobustnessData Augmentation	CodeCode Available
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness	Sep 15, 2022	Adversarial Robustness	—Unverified
Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries	Sep 14, 2022	Adversarial Robustness	—Unverified
Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering	Sep 14, 2022	Adversarial RobustnessQuestion Answering	—Unverified
On the interplay of adversarial robustness and architecture components: patches, convolution and attention	Sep 14, 2022	Adversarial Robustnessimage-classification	—Unverified
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack	Sep 14, 2022	3D ClassificationAdversarial Attack	CodeCode Available
FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices	Sep 8, 2022	Adversarial RobustnessFederated Learning	—Unverified
Adversarial Robustness for Tabular Data through Cost and Utility Awareness	Aug 27, 2022	Abuse DetectionAdversarial Robustness	—Unverified
FuncFooler: A Practical Black-box Attack Against Learning-based Binary Code Similarity Detection Methods	Aug 26, 2022	Adversarial RobustnessCode Generation	—Unverified
Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compression	Aug 26, 2022	Adversarial RobustnessDensity Estimation	—Unverified
Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs	Aug 26, 2022	Adversarial RobustnessFew-Shot Learning	CodeCode Available
Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training	Aug 26, 2022	Adversarial Robustness	—Unverified
GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks	Aug 26, 2022	Adversarial RobustnessParameter Prediction	—Unverified
Shortcut Learning of Large Language Models in Natural Language Understanding	Aug 25, 2022	Adversarial RobustnessNatural Language Understanding	—Unverified
Different Spectral Representations in Optimized Artificial Neural Networks and Brains	Aug 22, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available
BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning	Aug 22, 2022	Adversarial Robustnessreinforcement-learning	—Unverified
Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective	Aug 20, 2022	Adversarial Robustnessimage-classification	CodeCode Available
Two Heads are Better than One: Robust Learning Meets Multi-branch Models	Aug 17, 2022	Adversarial RobustnessPhilosophy	CodeCode Available
On the Privacy Effect of Data Enhancement via the Lens of Memorization	Aug 17, 2022	Adversarial RobustnessData Augmentation	CodeCode Available
Self-Knowledge Distillation via Dropout	Aug 11, 2022	Adversarial Robustnessimage-classification	—Unverified
Adversarial robustness of VAEs through the lens of local geometry	Aug 8, 2022	Adversarial RobustnessDecoder	CodeCode Available
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks	Aug 7, 2022	Adversarial RobustnessRobust classification	—Unverified

Show:10 25 50

← PrevPage 42 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