SecurityResearchData

MosaicLeaks: research agents can leak company secrets via harmless web queries — RL fix reduces leakage

The key point: MosaicLeaks demonstrates that deep research agents can reveal private enterprise facts through seemingly ordinary web queries and proposes Privacy‑Aware Deep Research (PA‑DR) to cut leakage significantly.

In detail

  • MosaicLeaks creates a multi‑hop task mixing public and private information to evaluate leakage via query logs
  • Agents frequently leak private information; optimizing solely for task performance increases leakage
  • PA‑DR raises strict chain success from 48.7% to 58.7% and reduces answer/full‑information leakage from 34.0% to 9.9%

Why it matters

Businesses using agents that combine internal docs with external tools face a real risk that observers can reconstruct secrets from outbound queries; the paper’s mitigation offers a practical training approach to reduce that risk.

For you Actionable takeaway: Audit agent query outputs for leakage, restrict external queries when agents access sensitive docs, and consider privacy‑aware training or filtering before production use.

← All news

Summaries are generated automatically and link to the original source.