Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

Ähnliche Einträge

• On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
  von: Li, Binghui, et al.
  Veröffentlicht: (2023)
• Provably learning a multi-head attention layer
  von: Chen, Sitan, et al.
  Veröffentlicht: (2024)
• Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression
  von: Yan, Tingkai, et al.
  Veröffentlicht: (2025)
• Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
  von: Li, Binghui, et al.
  Veröffentlicht: (2024)
• Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
  von: Hong, Hanbin, et al.
  Veröffentlicht: (2023)