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 701–725 of 1746 papers

Title	Date	Tasks	Status	Hype
Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizations	Mar 15, 2023	Adversarial Robustness	—Unverified	0
Model-tuning Via Prompts Makes NLP Models Adversarially Robust	Mar 13, 2023	Adversarial RobustnessLanguage Modelling	CodeCode Available	0
Robustness-preserving Lifelong Learning via Dataset Condensation	Mar 7, 2023	Adversarial RobustnessDataset Condensation	—Unverified	0
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes	Mar 4, 2023	Adversarial RobustnessDiversity	CodeCode Available	0
Adversarial Attacks on Machine Learning in Embedded and IoT Platforms	Mar 3, 2023	Adversarial RobustnessModel Compression	—Unverified	0
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks	Mar 2, 2023	Adversarial Robustness	—Unverified	0
Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression	Mar 2, 2023	Adversarial RobustnessPrediction	CodeCode Available	1
Single Image Backdoor Inversion via Robust Smoothed Classifiers	Mar 1, 2023	Adversarial RobustnessImage Generation	CodeCode Available	1
SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases	Feb 28, 2023	Adversarial RobustnessNatural Language Inference	—Unverified	0
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking	Feb 28, 2023	Adversarial RobustnessBenchmarking	—Unverified	0
CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World	Feb 27, 2023	Adversarial Robustness	CodeCode Available	1
Randomness in ML Defenses Helps Persistent Attackers and Hinders Evaluators	Feb 27, 2023	Adversarial Robustness	—Unverified	0
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective	Feb 22, 2023	Adversarial RobustnessChatbot	—Unverified	0
Delving into the Adversarial Robustness of Federated Learning	Feb 19, 2023	Adversarial RobustnessFederated Learning	—Unverified	0
A Novel Noise Injection-based Training Scheme for Better Model Robustness	Feb 17, 2023	Adversarial RobustnessComputational Efficiency	—Unverified	0
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions	Feb 17, 2023	Adversarial RobustnessFairness	—Unverified	0
Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition	Feb 17, 2023	Adversarial RobustnessFairness	—Unverified	0
Adversarial Contrastive Distillation with Adaptive Denoising	Feb 17, 2023	Adversarial RobustnessDenoising	—Unverified	0
XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars	Feb 15, 2023	Adversarial RobustnessNeural Architecture Search	—Unverified	0
IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness	Feb 9, 2023	Adversarial Robustness	CodeCode Available	0
Robustness Implies Fairness in Causal Algorithmic Recourse	Feb 7, 2023	Adversarial RobustnessFairness	CodeCode Available	0
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks	Feb 6, 2023	Adversarial RobustnessImage Segmentation	—Unverified	0
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks	Feb 6, 2023	Adversarial RobustnessData Augmentation	CodeCode Available	0
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness	Feb 6, 2023	Adversarial Robustness	CodeCode Available	1
Rethinking Robust Contrastive Learning from the Adversarial Perspective	Feb 5, 2023	Adversarial RobustnessContrastive Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 29 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