Re-masking committed refusal tokens plus compliance prefixes bypasses safety in diffusion language models at 74-98% success across tested models.
The devil behind the mask: An emergent safety vulnerability of diffusion llms
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
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 jailbreaks dVLMs by globally optimizing probabilities in the denoising process to bypass refusal patterns, achieving stealthy and transferable attacks.
DLMs exhibit lower n-gram entropy, higher semantic coherence, and higher semantic diversity than ARMs, primarily due to bidirectional context and remasking decoding strategies.
citing papers explorer
-
Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models
Re-masking committed refusal tokens plus compliance prefixes bypasses safety in diffusion language models at 74-98% success across tested models.
-
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.
-
Differences in Text Generated by Diffusion and Autoregressive Language Models
DLMs exhibit lower n-gram entropy, higher semantic coherence, and higher semantic diversity than ARMs, primarily due to bidirectional context and remasking decoding strategies.