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 1501–1525 of 1746 papers

Title	Date	Tasks	Status
Improving Model Robustness with Latent Distribution Locally and Globally	Jul 8, 2021	Adversarial Robustness	CodeCode Available
Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection	Dec 13, 2022	Adversarial Attack DetectionAdversarial Defense	CodeCode Available
AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks	May 30, 2018	Adversarial Robustness	CodeCode Available
Stratified Adversarial Robustness with Rejection	May 2, 2023	Adversarial RobustnessRobust classification	CodeCode Available
RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features	Apr 16, 2025	Adversarial RobustnessComputational Efficiency	CodeCode Available
Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling	Feb 24, 2022	Adversarial Robustness	CodeCode Available
VideoPure: Diffusion-based Adversarial Purification for Video Recognition	Jan 25, 2025	Adversarial DefenseAdversarial Purification	CodeCode Available
Disentangling Adversarial Robustness and Generalization	Dec 3, 2018	Adversarial Robustness	CodeCode Available
Towards Robust LLMs: an Adversarial Robustness Measurement Framework	Apr 24, 2025	Adversarial RobustnessComputational Efficiency	CodeCode Available
Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection	Mar 27, 2023	Adversarial RobustnessOut-of-Distribution Detection	CodeCode Available
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients	Nov 26, 2017	Adversarial Robustness	CodeCode Available
Diffusion-based Adversarial Purification for Intrusion Detection	Jun 25, 2024	Adversarial PurificationAdversarial Robustness	CodeCode Available
Improving the Adversarial Robustness of NLP Models by Information Bottleneck	Jun 11, 2022	Adversarial RobustnessSST-2	CodeCode Available
Adversarial Attacks on Data Attribution	Sep 9, 2024	Adversarial AttackAdversarial Robustness	CodeCode Available
Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library	Apr 27, 2024	Adversarial RobustnessNon-Adversarial Robustness	CodeCode Available
Advancing Adversarial Robustness in GNeRFs: The IL2-NeRF Attack	Jan 1, 2025	3D ReconstructionAdversarial Attack	CodeCode Available
Understanding Intrinsic Robustness Using Label Uncertainty	Jul 7, 2021	Adversarial RobustnessClassification	CodeCode Available
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks	Dec 4, 2022	Adversarial RobustnessInductive Bias	CodeCode Available
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks	May 19, 2020	Adversarial RobustnessGeneral Classification	CodeCode Available
DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination	Oct 31, 2024	Adversarial RobustnessBinarization	CodeCode Available
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis	Oct 2, 2022	Adversarial Robustness	CodeCode Available
Individual Fairness in Bayesian Neural Networks	Apr 21, 2023	Adversarial RobustnessBayesian Inference	CodeCode Available
Adversarially Robust One-class Novelty Detection	Aug 25, 2021	Adversarial RobustnessNovelty Detection	CodeCode Available
Inducing Data Amplification Using Auxiliary Datasets in Adversarial Training	Sep 27, 2022	Adversarial Robustness	CodeCode Available
Different Spectral Representations in Optimized Artificial Neural Networks and Brains	Aug 22, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available

Show:10 25 50

← PrevPage 61 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