Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning

Published
Source
arXiv
Paper number
1481
Field
AI / Agents
arXiv ID
2611.20045

Key points

  • The paper presents a unified threat model splitting deep research agents into retrieval, planning, evidence integration, and report generation.
  • Coding 34 primary studies showed that only 26.5% involve the planning stage and none performs end-to-end poisoning evaluation on commercial products.
  • The authors proposed the agenda seeding attack, which writes no instructions and only introduces a fictitious evaluation metric.
  • Across 3,520 sandboxed research runs under the same budget, GEO and prompt injection were nearly ineffective.
  • Agenda seeding made the attacker's target the top pick in 16% to 28% of reports.
  • Provenance tagging preserved utility but could be bypassed by multi-site bait.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)