Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Documenti analoghi

• Guarding Multiple Secrets: Enhanced Summary Statistic Privacy for Data Sharing
  di: Wang, Shuaiqi, et al.
  Pubblicazione: (2024)
• GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?
  di: Li, Mufei, et al.
  Pubblicazione: (2023)
• On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
  di: Wei, Rongzhe, et al.
  Pubblicazione: (2023)
• Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls
  di: Selvi, Aras, et al.
  Pubblicazione: (2024)
• Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
  di: Wei, Rongzhe, et al.
  Pubblicazione: (2025)