Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction

Documenti analoghi

• Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
  di: Li, Yanming, et al.
  Pubblicazione: (2025)
• EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling
  di: Song, Zichen, et al.
  Pubblicazione: (2024)
• Revisiting Locally Differentially Private Protocols: Towards Better Trade-offs in Privacy, Utility, and Attack Resistance
  di: Arcolezi, Héber H., et al.
  Pubblicazione: (2025)
• Private Frequency Estimation Via Residue Number Systems
  di: Arcolezi, Héber H.
  Pubblicazione: (2025)
• LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
  di: Ibanez-Lissen, Luis, et al.
  Pubblicazione: (2024)