Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier

Documenti analoghi

• Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers
  di: Jin, Gaojie, et al.
  Pubblicazione: (2025)
• CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
  di: Wang, Zixia, et al.
  Pubblicazione: (2025)
• Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments
  di: Jin, Gaojie, et al.
  Pubblicazione: (2024)
• Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network
  di: Wu, Dengyu, et al.
  Pubblicazione: (2024)
• Certified Adversarial Robustness via Partition-based Randomized Smoothing
  di: Goli, Hossein, et al.
  Pubblicazione: (2024)