SEEK, a black-box agent, can steal scientific agents' skills
Start here
Researchers from City University of Hong Kong and other institutions propose the black-box self-evolving red-team agent SEEK, which accumulates response evidence through persistent memory and evolves reusable interaction patterns into attack skills, for extracting protected skills from scientific Agent platforms. The benchmark covers 40 protected skills across eight open-source and closed-source platforms, and the results show that all eight platforms leak at least one skill, with four platforms reaching a 100% attack success rate under a single direct request.
Generated by AI from reports · Updated 17 days ago
Attention and developments
Attention, hourly
Now 39, 0% in 24 hours·Peak 39 (Nov 7 01:00)
Related research
This event's paper
- SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents
arXiv · 2026-10-25 · Deep reading
Progress timeline
- arXiv: Jailbreaks, Prompt Injection, Poisoning & DefensesSelectedSEEK: evolutionary knowledge skill extraction against frontier scientific agents
Researchers from City University of Hong Kong and other institutions propose a black-box self-evolving red-teaming agent, SEEK, which accumulates response evidence through persistent memory and evolves reusable interaction patterns into attack skills, used to extract protected skills from scientific agent platforms. The benchmark covers 40 protected skills across eight open-source and closed-source scientific agent platforms, and the results show that all eight platforms leaked at least one skill, with four platforms reaching a 100% attack success rate under a single direct request. On 12 skills of SpatialAgent and Biomni, SEEK extracted all of them, reducing the average number of turns to first success by 31.8% and 38.2% respectively compared with BGIP. On OpenScience, an instruction-confidentiality policy that blocked three benchmark protocols was still extracted by SEEK for one of six protected skills. The paper accordingly concludes that current scientific agents cannot reliably protect their skills, and that defense evaluation needs to cover adaptive multi-turn attackers that accumulate evidence across turns.