# Hugging Face — MosaicLeaks: Can your research agent keep a secret?

- Company: Hugging Face (huggingface.co)
- Announced: 2026-06-18T18:13:13+00:00
- Category: research-paper
- Subject: Platform
- Source: https://huggingface.co/blog/ServiceNow/mosaicleaks
- Record: https://forck.live/items/1479-mosaicleaks-can-your-research-agent-keep-a-secret

Introduces MosaicLeaks, a benchmark for evaluating privacy leakage in deep research agents, and proposes Privacy-Aware Deep Research (PA-DR) training that reduces answer/full-information leakage from 34.0% to 9.9% while improving strict chain success from 48.7% to 58.7%.

## Evidence

Verbatim from https://huggingface.co/blog/ServiceNow/mosaicleaks:

> MosaicLeaks proposes a new deep-research task with multi-hop questions that interleave public and private information. Across the models we tested, agents frequently leaked private information, and training only for task performance made it worse. We propose a mosaic-leakage-aware RL training method, Privacy-Aware Deep Research (PA-DR), which raises strict chain success (the share of chains where every hop is answered correctly) from 48.7% to 58.7% while reducing answer/full-information leakage from 34.0% to 9.9%.

---

Record: https://forck.live/items/1479-mosaicleaks-can-your-research-agent-keep-a-secret
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md