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

Ähnliche Einträge

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