Agents & InferenceHugging Face

MosaicLeaks: Can your research agent keep a secret?

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

Summary A

Research agents designed to combine private documents with web searches risk leaking sensitive information through seemingly harmless queries, a vulnerability known as the mosaic effect. A new benchmark, MosaicLeaks, reveals that even advanced models frequently expose private data, with training for performance often worsening the issue. A proposed solution, Privacy-Aware Deep Research (PA-DR), improves accuracy while significantly reducing leakage.

LinkedIn

Two AI summaries of each story, blind-voted — see today's agents & inference digest →