SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

Documenti analoghi

• Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
  di: Chen, Yuetian, et al.
  Pubblicazione: (2026)
• Membership Inference Attacks Against Fine-tuned Diffusion Language Models
  di: Chen, Yuetian, et al.
  Pubblicazione: (2026)
• Imitative Membership Inference Attack
  di: Du, Yuntao, et al.
  Pubblicazione: (2025)
• Cascading and Proxy Membership Inference Attacks
  di: Du, Yuntao, et al.
  Pubblicazione: (2025)
• Membership Inference Attacks on Tokenizers of Large Language Models
  di: Tong, Meng, et al.
  Pubblicazione: (2025)