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 1101–1150 of 1746 papers

TitleStatusHype
Towards Robustness of Deep Neural Networks via Regularization—0
Adversarial Robustness of Deep Sensor Fusion Models—0
Towards Robust Vision Transformer via Masked Adaptive Ensemble—0
Towards Stable and Robust AdderNets—0
Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning—0
Towards the Memorization Effect of Neural Networks in Adversarial Training—0
Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives—0
Towards Understanding and Improving Adversarial Robustness of Vision Transformers—0
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks—0
Towards unlocking the mystery of adversarial fragility of neural networks—0
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks—0
Trace-Norm Adversarial Examples—0
Trading Inference-Time Compute for Adversarial Robustness—0
Training Robust Deep Neural Networks via Adversarial Noise Propagation—0
Training Safe Neural Networks with Global SDP Bounds—0
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders—0
Transfer of Adversarial Robustness Between Perturbation Types—0
Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness—0
Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection—0
Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models—0
UFO-BLO: Unbiased First-Order Bilevel Optimization—0
Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks—0
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric—0
Understanding Adversarially Robust Generalization via Weight-Curvature Index—0
Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin—0
Understanding Adversarial Robustness Through Loss Landscape Geometries—0
Understanding and Measuring Robustness of Multimodal Learning—0
Understanding the Impact of Graph Reduction on Adversarial Robustness in Graph Neural Networks—0
Understanding the Interplay between Privacy and Robustness in Federated Learning—0
Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks—0
Universal Adversarial Framework to Improve Adversarial Robustness for Diabetic Retinopathy Detection—0
Universal Adversarial Training with Class-Wise Perturbations—0
Classifier-independent Lower-Bounds for Adversarial Robustness—0
Universally Robust Graph Neural Networks by Preserving Neighbor Similarity—0
Unlabeled Data Help: Minimax Analysis and Adversarial Robustness—0
Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights—0
Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness—0
Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models—0
Unsupervised Adversarially-Robust Representation Learning on Graphs—0
Unveiling Project-Specific Bias in Neural Code Models—0
Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory—0
Use of small auxiliary networks and scarce data to improve the adversarial robustness of deep learning models—0
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples—0
Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness—0
Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions—0
Variational Autoencoders: A Harmonic Perspective—0
Variational Randomized Smoothing for Sample-Wise Adversarial Robustness—0
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks—0
Visual Interpretability Alone Helps Adversarial Robustness—0
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models—0
Show:102550
← PrevPage 23 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