Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric

Documenti analoghi

• Position: Contextual Integrity is Inadequately Applied to Language Models
  di: Shvartzshnaider, Yan, et al.
  Pubblicazione: (2025)
• On the Alignment of Group Fairness with Attribute Privacy
  di: Aalmoes, Jan, et al.
  Pubblicazione: (2022)
• Trustless Audits without Revealing Data or Models
  di: Waiwitlikhit, Suppakit, et al.
  Pubblicazione: (2024)
• A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures
  di: Nguyen, Thanh Tam, et al.
  Pubblicazione: (2024)
• Locket: Robust Feature-Locking Technique for Language Models
  di: He, Lipeng, et al.
  Pubblicazione: (2025)