SOURCE-LINKED INTELLIGENCE

Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the privacy risks of DLMs remain underexplored. We identify a phenomenon termed token-level memorization asymmetry through theoretical analysis of diffusion training dynamics. Building on this finding, we propose Q-Skew, a quantile-weighted skewness-based indicator for membership inference on finetuned DLMs. Experiments across multiple fine-

Read original source ↗ Open in workspace

recordType

paper

region

Global