BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints

Documenti analoghi

• Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
  di: Miranda, Michele, et al.
  Pubblicazione: (2024)
• MeanCache: User-Centric Semantic Caching for LLM Web Services
  di: Gill, Waris, et al.
  Pubblicazione: (2024)
• Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
  di: Chen, Sixu, et al.
  Pubblicazione: (2026)
• When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
  di: Tian, Huan, et al.
  Pubblicazione: (2023)
• SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
  di: Zhang, Hanxiu, et al.
  Pubblicazione: (2025)