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 351–400 of 1746 papers

TitleStatusHype
A Fundamental Accuracy--Robustness Trade-off in Regression and Classification—0
A Frequency Perspective of Adversarial Robustness—0
Adversarial Prompt Distillation for Vision-Language Models—0
DensePure: Understanding Diffusion Models towards Adversarial Robustness—0
A Framework for Verification of Wasserstein Adversarial Robustness—0
A Flat Minima Perspective on Understanding Augmentations and Model Robustness—0
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness—0
A Finer Calibration Analysis for Adversarial Robustness—0
Affine-Invariant Robust Training—0
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend—0
Adversarial Masked Autoencoder Purifier with Defense Transferability—0
AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning—0
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives—0
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm—0
Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs—0
Discretization based Solutions for Secure Machine Learning against Adversarial Attacks—0
Delving into Decision-based Black-box Attacks on Semantic Segmentation—0
Delving into Feature Space: Improving Adversarial Robustness by Feature Spectral Regularization—0
Adversarially Robust Video Perception by Seeing Motion—0
Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers—0
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception—0
Delving into the Adversarial Robustness of Federated Learning—0
Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuning—0
Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits—0
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction—0
Adversarial Test on Learnable Image Encryption—0
Adversarial Robustness with Semi-Infinite Constrained Learning—0
Adversarially Robust Streaming Algorithms via Differential Privacy—0
Defense-PointNet: Protecting PointNet Against Adversarial Attacks—0
Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach—0
Adversarially Robust Spiking Neural Networks with Sparse Connectivity—0
Label Augmentation for Neural Networks Robustness—0
Adversarial Robustness: What fools you makes you stronger—0
Advancing Adversarial Training by Injecting Booster Signal—0
Achieving Adversarial Robustness via Sparsity—0
Defense Through Diverse Directions—0
Adversarial robustness via stochastic regularization of neural activation sensitivity—0
Adversarial Robustness via Runtime Masking and Cleansing—0
Adversarial Robustness of Link Sign Prediction in Signed Graphs—0
Advancing Adversarial Robustness Through Adversarial Logit Update—0
A3E: Aligned and Augmented Adversarial Ensemble for Accurate, Robust and Privacy-Preserving EEG Decoding—0
Defending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems—0
Adversarially Robust Neural Networks via Optimal Control: Bridging Robustness with Lyapunov Stability—0
Adversarial Robustness via Label-Smoothing—0
Adversary Agnostic Robust Deep Reinforcement Learning—0
Adversarial Robustness via Adaptive Label Smoothing—0
Adversarially Robust Neural Architectures—0
Achieving Adversarial Robustness Requires An Active Teacher—0
DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks—0
Defending Against Adversarial Examples by Regularized Deep Embedding—0
Show:102550
← PrevPage 8 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