Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation

ArXi:2605.22060v1 Announce Type: cross Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker can repeatedly query the service, collect large volumes of released synthetic images, and use them as