Documenti analoghi

• Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
  di: Rashid, Md Rafi Ur, et al.
  Pubblicazione: (2023)
• Smoothed Embeddings for Robust Language Models
  di: Hase, Ryo, et al.
  Pubblicazione: (2025)
• Directional Embedding Smoothing for Robust Vision Language Models
  di: Wang, Ye, et al.
  Pubblicazione: (2026)
• Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
  di: Khattar, Vanshaj, et al.
  Pubblicazione: (2026)
• Analyzing Inference Privacy Risks Through Gradients in Machine Learning
  di: Li, Zhuohang, et al.
  Pubblicazione: (2024)