Dynamics of covert signaling: Modeling the emergence and extinction of identity signals

Covert identity signals permit the communication of group membership to ingroup members while avoiding potentially costly detection by members of other groups. If individuals are incentivized to detect others' group memberships, however, covert signals may not remain covert for very long. We propose a theoretical extension to the literature on covert signaling in which conventionalized identity signals can become destabilized when learned by outgroup individuals, to be replaced by the emergence of new signaling conventions. We formalize this idea with both analytical and agent-based modeling of ingroup and outgroup individuals who to learn about signals of group membership. Depending on the risk and associated cost of detection by the outgroup, the model yields three dynamic classes: saturation, where all identity signals become stable conventions and never go extinct; cycling, in which new signals emerge to replace old ones as they are learned by the outgroup; and suppression, in which informative identity signals never emerge. Our analysis has implications for understanding identity signaling, the emergence of conventions, coded speech, and the ebb and flow of fashion cycles.