Unaware Adversaries: A Framework for Characterizing Emergent Conflict Between Non-Coordinating Agents
Scott VanRavenswaay's paper defines "unaware adversaries": agents that work against each other without knowing it, each pursuing a local objective and coupled only through a shared environment, with no channel for deconfliction. The canonical example is a room with a radiator on a building thermostat and a window air conditioner on its own controls, locked in "persistent, mutually negating work". From case studies of closed-loop, open-loop and designed conflicts, among them generative adversarial networks and the 2008 incident in which Pakistan Telecom's block of YouTube spread across the internet, the paper builds a taxonomy, and uses the framework to propose mitigations: a "Pedagogical GAN", and a Gradient-Paced BGP Advertiser that throttles agents "whose announcements produce outsized ripples in routing state".
Was this useful?