SOTAVerified

Adversarial Robustness

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 901–950 of 1746 papers

TitleStatusHype
Are models trained on temporally-continuous data streams more adversarially robust?—0
Understanding the Impact of Graph Reduction on Adversarial Robustness in Graph Neural Networks—0
Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning—0
The Dilemma Between Data Transformations and Adversarial Robustness for Time Series Application Systems—0
The Diversity Metrics of Sub-models based on SVD of Jacobians for Ensembles Adversarial Robustness—0
Improving Fast Adversarial Training via Self-Knowledge Guidance—0
Are classical deep neural networks weakly adversarially robust?—0
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning—0
Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN—0
Improving Graph Neural Networks via Adversarial Robustness Evaluation—0
Improving Hierarchical Adversarial Robustness of Deep Neural Networks—0
Improving Hyperspectral Adversarial Robustness Under Multiple Attacks—0
Improving Interpretability via Regularization of Neural Activation Sensitivity—0
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks—0
Improving out-of-distribution generalization via multi-task self-supervised pretraining—0
Improving Performance of Semi-Supervised Learning by Adversarial Attacks—0
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization—0
Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks—0
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning—0
Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning—0
Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?—0
Improving Robustness with Image Filtering—0
Architectural Adversarial Robustness: The Case for Deep Pursuit—0
The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networks—0
ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks—0
The Effects of Image Distribution and Task on Adversarial Robustness—0
Improving Calibration through the Relationship with Adversarial Robustness—0
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training—0
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing—0
The Importance of Robust Features in Mitigating Catastrophic Forgetting—0
Increasing Confidence in Adversarial Robustness Evaluations—0
The Intrinsic Dimension of Images and Its Impact on Learning—0
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense—0
Indirect Gradient Matching for Adversarial Robust Distillation—0
Understanding the Interplay between Privacy and Robustness in Federated Learning—0
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness—0
The Lipschitz Constant of Self-Attention—0
Adversarially Robust Bloom Filters: Privacy, Reductions, and Open Problems—0
The Many Faces of Adversarial Risk—0
Inter-frame Accelerate Attack against Video Interpolation Models—0
Theoretical Analysis of Adversarial Learning: A Minimax Approach—0
A Primer on Multi-Neuron Relaxation-based Adversarial Robustness Certification—0
Interpretable Graph Capsule Networks for Object Recognition—0
Interpreting Adversarial Examples by Activation Promotion and Suppression—0
Interpreting Adversarial Robustness: A View from Decision Surface in Input Space—0
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity—0
Intriguing class-wise properties of adversarial training—0
Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs—0
Intriguing Properties of Adversarial Examples—0
Intriguing properties of adversarial training at scale—0
Show:102550
← PrevPage 19 of 35Next →
All datasetsAdvGLUECIFAR-10ImageNetImageNet-AImageNet-CStylized ImageNetCIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeBERTa (single model)Accuracy0.61—Unverified
2ALBERT (single model)Accuracy0.59—Unverified
3T5 (single model)Accuracy0.57—Unverified
4SMART_RoBERTa (single model)Accuracy0.54—Unverified
5FreeLB (single model)Accuracy0.5—Unverified
6RoBERTa (single model)Accuracy0.5—Unverified
7InfoBERT (single model)Accuracy0.46—Unverified
8ELECTRA (single model)Accuracy0.42—Unverified
9BERT (single model)Accuracy0.34—Unverified
10SMART_BERT (single model)Accuracy0.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Mixed classifierAccuracy95.23—Unverified
2Stochastic-LWTA/PGD/WideResNet-34-10Accuracy92.26—Unverified
3Stochastic-LWTA/PGD/WideResNet-34-5Accuracy91.88—Unverified
4GLOT-DRAccuracy84.13—Unverified
5TRADES-ANCRA/ResNet18Accuracy81.7—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-50 (SGD, Cosine)Accuracy77.4—Unverified
2ResNet-50 (SGD, Step)Accuracy76.9—Unverified
3DeiT-S (AdamW, Cosine)Accuracy76.8—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy76.4—Unverified
#ModelMetricClaimedVerifiedStatus
1DeiT-S (AdamW, Cosine)Accuracy12.2—Unverified
2ResNet-50 (SGD, Cosine)Accuracy3.3—Unverified
3ResNet-50 (SGD, Step)Accuracy3.2—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy3.1—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-50 (AdamW, Cosine)mean Corruption Error (mCE)59.3—Unverified
2ResNet-50 (SGD, Step)mean Corruption Error (mCE)57.9—Unverified
3ResNet-50 (SGD, Cosine)mean Corruption Error (mCE)56.9—Unverified
4DeiT-S (AdamW, Cosine)mean Corruption Error (mCE)48—Unverified
#ModelMetricClaimedVerifiedStatus
1DeiT-S (AdamW, Cosine)Accuracy13—Unverified
2ResNet-50 (SGD, Cosine)Accuracy8.4—Unverified
3ResNet-50 (SGD, Step)Accuracy8.3—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy8.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Mixed ClassifierClean Accuracy85.21—Unverified
2ResNet18/MART-ANCRAClean Accuracy60.1—Unverified