Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models

ArXi:2605.19698v1 Announce Type: cross Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapted and redistributed by multiple independent parties, allowing multiple concept-specific trigger-target associations to accumulate in the same model.