CMU researcher warns aggregated chatbot analysis can leak sensitive research insights
niloofar_mire · x · 2026-11-17
In an interview with Science, CMU CyLab faculty member Nilofar Mirel highlights how AI companies' analysis of aggregated chatbot conversations could inadvertently reveal sensitive research insights, even without directly exposing individual conversations — a privacy concern for industry data practices.
More from Safety
- US tightens controls on remote access to AI technology amid Nvidia fallout — nordicinst · 2026-11-17
- heybox: Open-Source Touch ID Lock Stops AI Agents From Reading Your HEY Email — seanmcdonaldxyz · 2026-11-17
- Breach of third-party JS host impacts hundreds of high-value websites — Kyrannio · 2026-11-17
- Researchers Find Undocumented x86 Instructions Allowing User-Space Microcode Writes — sull · 2026-11-17
- Nina Schick links wave of outages to spreading AI zero-day capabilities — NinaDSchick · 2026-11-17
- LangChain adds host allowlists to Managed Deep Agents, blocking injected exfil via proxy — hwchase17 · 2026-11-17