Risk-Aware Privacy Preservation for LLM Inference
Summary
When users send prompts to LLM services like ChatGPT, sensitive personal information (such as names, addresses, or ID numbers) can leak out, even when basic privacy protections are used. This paper presents Rap-LI, a framework that identifies which parts of a user's input contain sensitive data and applies stronger privacy protection to those specific parts, rather than treating all data equally.
Classification
Affected Vendors
Related Issues
GHSA-382c-vx95-w3p5: Gittensory: Missing contributor-scoped access control on profile endpoint and MCP tool leaks miner financial data
CVE-2025-45150: Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive
Original source: http://ieeexplore.ieee.org/document/11409403
First tracked: March 16, 2026 at 04:14 PM
Classified by LLM (prompt v3) · confidence: 92%