BadDLM implants effective backdoors in diffusion language models across concept, attribute, alignment, and payload targets by exploiting denoising dynamics while preserving clean performance.
The devil behind the mask: An emergent safety vulnerability of diffusion llms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
GPO-V jailbreaks dVLMs by globally optimizing probabilities in the denoising process to bypass refusal patterns, achieving stealthy and transferable attacks.
citing papers explorer
-
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
BadDLM implants effective backdoors in diffusion language models across concept, attribute, alignment, and payload targets by exploiting denoising dynamics while preserving clean performance.
-
GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
GPO-V jailbreaks dVLMs by globally optimizing probabilities in the denoising process to bypass refusal patterns, achieving stealthy and transferable attacks.