Boundary-targeted Membership Inference Attacks on Safety Classifiers

Documenti analoghi

• Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
  di: Naseh, Ali, et al.
  Pubblicazione: (2025)
• Position: Privacy Is Not Just Memorization!
  di: Mireshghallah, Niloofar, et al.
  Pubblicazione: (2025)
• Incorporating Attribution Importance for Improving Faithfulness Metrics
  di: Zhao, Zhixue, et al.
  Pubblicazione: (2023)
• The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
  di: Makroo, Owais, et al.
  Pubblicazione: (2025)
• Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
  di: Xue, Huiyin, et al.
  Pubblicazione: (2025)