Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Documenti analoghi

• A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
  di: Xin, Rui, et al.
  Pubblicazione: (2025)
• CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs
  di: Mireshghallah, Niloofar, et al.
  Pubblicazione: (2025)
• PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
  di: Bae, Yubeen, et al.
  Pubblicazione: (2025)
• Position: Privacy Is Not Just Memorization!
  di: Mireshghallah, Niloofar, et al.
  Pubblicazione: (2025)
• Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
  di: Naseh, Ali, et al.
  Pubblicazione: (2025)