SHADOWMASK backdoors MDLMs by modifying the forward corruption process with a trigger-mask mixture, achieving near-100% attack success while preserving clean utility on DiT-based and LLaDA models.
Text- to-image diffusion models can be easily backdoored through multimodal data poisoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Backdooring Masked Diffusion Language Models
SHADOWMASK backdoors MDLMs by modifying the forward corruption process with a trigger-mask mixture, achieving near-100% attack success while preserving clean utility on DiT-based and LLaDA models.