AI RESEARCH
Membership Inference Attacks on Discrete Diffusion Language Models
arXiv CS.LG
•
ArXi:2605.16445v1 Announce Type: new Masked Diffusion Language Models MDLMs replace autoregressive generation with iterative demasking and their privacy properties are largely unstudied. We study membership inference attacks MIA on fine tuned MDLMs and show they are significantly vulnerable than current grey box baselines suggest. We extract a 46 dimensional feature vector from the models reconstruction loss at four masking ratios and train XGBoost and MLP classifiers on top.