2 papers
cs.CY2026
Non-Great-Power Conflict and AI Risk
Kristina Kempkey, Seán Boddy, Catherine Ge-Wang
Research on advanced AI and the risk of war has focused almost exclusively on great power conflict, on the grounds that confrontation between nuclear-armed adversaries poses the gr…
cs.AI2026
Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety
Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad +3
An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but unt…