An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Documenti analoghi

• Cascade: Token-Sharded Private LLM Inference
  di: Thomas, Rahul, et al.
  Pubblicazione: (2025)
• Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
  di: Pal, Arka, et al.
  Pubblicazione: (2026)
• vTune: Verifiable Fine-Tuning for LLMs Through Backdooring
  di: Zhang, Eva, et al.
  Pubblicazione: (2024)
• Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions
  di: Pal, Arka, et al.
  Pubblicazione: (2025)
• Secure Aggregation is Not Private Against Membership Inference Attacks
  di: Ngo, Khac-Hoang, et al.
  Pubblicazione: (2024)