Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment

Documenti analoghi

• The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
  di: Makroo, Owais, et al.
  Pubblicazione: (2025)
• Mixture-Models: a one-stop Python Library for Model-based Clustering using various Mixture Models
  di: Kasa, Siva Rajesh, et al.
  Pubblicazione: (2024)
• DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
  di: Wang, Ziyi, et al.
  Pubblicazione: (2026)
• Approximating innovation potential with neurofuzzy robust model
  di: Richard Kasa
  Pubblicazione: (2015)
• Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
  di: Kasa, Siva Rajesh, et al.
  Pubblicazione: (2025)