Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks

Excerpt

arXiv:2610.00430v1 Announce Type: cross Abstract: Autonomous large language model (LLM) agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks include agent worms, which spread through self-replicating prompt injections or configuration compromises. We introduce \emph{memetic trojans}, a distinct class of network-mediated attack that exploits agents' tendencies to retransmit and amplify content. Unlike agent worms, whose propaga