Semantic-level Backdoor Attack against Text-to-Image Diffusion Models

ArXi:2602.04898v3 Announce Type: replace-cross Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. Existing attacks typically rely on fixed textual triggers and single-entity backdoor targets, making them highly susceptible to enumeration-based input defenses and attention-consistency detection. In this work, we propose Semantic-level Backdoor Attack (SemBD), which