Image de couverture de livre

Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Ruihan, Sun, Jun
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Certified Unlearning for Neural Networks
par: Koloskova, Anastasia, et autres
Publié: (2025)

Certified Defense on the Fairness of Graph Neural Networks
par: Dong, Yushun, et autres
Publié: (2023)

AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks
par: Lai, Yuni, et autres
Publié: (2025)

On Using Certified Training towards Empirical Robustness
par: De Palma, Alessandro, et autres
Publié: (2024)

Collective Certified Robustness against Graph Injection Attacks
par: Lai, Yuni, et autres
Publié: (2024)

Towards Generalized Certified Robustness with Multi-Norm Training
par: Jiang, Enyi, et autres
Publié: (2024)

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
par: Wu, Jiapeng, et autres
Publié: (2023)

Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement
par: Zhang, Chi, et autres
Publié: (2024)

Certified Causal Defense with Generalizable Robustness
par: Qiao, Yiran, et autres
Publié: (2024)

Position: Certified Robustness Does Not (Yet) Imply Model Security
par: Cullen, Andrew C., et autres
Publié: (2025)

FairProof : Confidential and Certifiable Fairness for Neural Networks
par: Yadav, Chhavi, et autres
Publié: (2024)

Robust Privacy: Inference-Time Privacy through Certified Robustness
par: Jin, Jiankai, et autres
Publié: (2026)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
par: Lyu, Saiyue, et autres
Publié: (2024)

A Robust Certified Machine Unlearning Method Under Distribution Shift
par: Guo, Jinduo, et autres
Publié: (2026)

CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization
par: Wang, Derui, et autres
Publié: (2025)

PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
par: Li, Xuran, et autres
Publié: (2025)

Multiplicative Reweighting for Robust Neural Network Optimization
par: Bar, Noga, et autres
Publié: (2021)

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
par: Abbahaddou, Yassine, et autres
Publié: (2024)

On the Adversarial Robustness of Graph Neural Networks with Graph Reduction
par: Wu, Kerui, et autres
Publié: (2024)

Certifiably Robust RAG against Retrieval Corruption
par: Xiang, Chong, et autres
Publié: (2024)

Supervised Robustness-preserving Data-free Neural Network Pruning
par: Meng, Mark Huasong, et autres
Publié: (2022)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
par: Zhang, Yuhao, et autres
Publié: (2023)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
par: Gosch, Lukas, et autres
Publié: (2024)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
par: Brown, Gavin, et autres
Publié: (2024)

Cross-Input Certified Training for Universal Perturbations
par: Xu, Changming, et autres
Publié: (2024)

CERT-ED: Certifiably Robust Text Classification for Edit Distance
par: Huang, Zhuoqun, et autres
Publié: (2024)

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
par: Dai, Enyan, et autres
Publié: (2022)

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
par: Kalinin, Nikita P., et autres
Publié: (2025)

Towards Strong Certified Defense with Universal Asymmetric Randomization
par: Hong, Hanbin, et autres
Publié: (2025)

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
par: Lou, Qian, et autres
Publié: (2024)

How Does Bayes Error Limit Probabilistic Robust Accuracy
par: Zhang, Ruihan, et autres
Publié: (2024)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
par: Hong, Hanbin, et autres
Publié: (2023)

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
par: Zhang, Xinyu, et autres
Publié: (2023)

Certifiably Robust Image Watermark
par: Jiang, Zhengyuan, et autres
Publié: (2024)

DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks
par: Khaled, Kacem, et autres
Publié: (2025)

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
par: Huang, Zhuoqun, et autres
Publié: (2025)

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
par: Fu, Chengyan, et autres
Publié: (2024)

Certified Machine Unlearning via Noisy Stochastic Gradient Descent
par: Chien, Eli, et autres
Publié: (2024)

A Certified Unlearning Approach without Access to Source Data
par: Basaran, Umit Yigit, et autres
Publié: (2025)

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
par: Yang, Han, et autres
Publié: (2025)