New preprint: simulating AI-enabled influence campaigns at scale
A new preprint on arXiv, coauthored by CDI faculty member Jonas R. Kunst, introduces IO Factory, a framework that simulates coordinated AI-driven influence campaigns as traceable end-to-end processes and evaluates them across configurations of up to 100,000 agents.
A new framework, IO Factory, that simulates AI-enabled influence campaigns end to end—from planning and platform action to exposure, interpretation, and adaptation—inside a controlled synthetic platform. Tested across configurations of up to 100,000 agents, it executes campaign timelines at scale and produces inspectable records of exposure and measured shifts in configured belief variables, supporting reproducible research and red-team analysis of coordinated manipulation.