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 951–1000 of 1746 papers

TitleStatusHype
RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses—0
Robust Certification for Laplace Learning on Geometric Graphs—0
Robust Collective Classification against Structural Attacks—0
Robust Dataset Distillation by Matching Adversarial Trajectories—0
Adversarial Robustness through Bias Variance Decomposition: A New Perspective for Federated Learning—0
Robust Decentralized Learning with Local Updates and Gradient Tracking—0
Robust Deep Learning Ensemble against Deception—0
Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples—0
RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems—0
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack—0
Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks—0
Robustified Domain Adaptation—0
Robust Information Retrieval—0
Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms—0
Robust low-rank training via approximate orthonormal constraints—0
RobustMQ: Benchmarking Robustness of Quantized Models—0
Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium—0
Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes—0
Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach—0
Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates—0
Robustness Implies Privacy in Statistical Estimation—0
A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?—0
Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy—0
Robustness of deep learning classification to adversarial input on GPUs: asynchronous parallel accumulation is a source of vulnerability—0
Robustness of Explanation Methods for NLP Models—0
Testing robustness of predictions of trained classifiers against naturally occurring perturbations—0
Robustness Of Saak Transform Against Adversarial Attacks—0
Robustness-preserving Lifelong Learning via Dataset Condensation—0
Robust Physical-World Attacks on Face Recognition—0
Robust Proxy: Improving Adversarial Robustness by Robust Proxy Learning—0
Robust Regularization with Adversarial Labelling of Perturbed Samples—0
Robust Subgraph Learning by Monitoring Early Training Representations—0
Robust Survival Analysis with Adversarial Regularization—0
Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning—0
Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries—0
Robust Transfer Learning with Pretrained Language Models through Adapters—0
Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks—0
RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization—0
RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models—0
RUSH: Robust Contrastive Learning via Randomized Smoothing—0
SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models—0
LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks—0
Sample Complexity of Adversarially Robust Linear Classification on Separated Data—0
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings—0
Scalable Lipschitz Estimation for CNNs—0
Scalable Neural Learning for Verifiable Consistency with Temporal Specifications—0
Scalable Quantitative Verification For Deep Neural Networks—0
Scalable Whitebox Attacks on Tree-based Models—0
Scoring Black-Box Models for Adversarial Robustness—0
Second Order Optimization for Adversarial Robustness and Interpretability—0
Show:102550
← PrevPage 20 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