Membership Inference Attacks Against Fine-tuned Diffusion Language Models

ICLR 2026 Conference Submission20589 Authors

Keywords: Membership Inference Attack, LLM, AI Privacy

TL;DR: SAMA: First membership inference attack exposing privacy vulnerabilities in Diffusion Language Models. Achieves 8× better detection than existing methods through robust sign-based aggregation of multiple mask configurations.

Abstract: Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains critically underexplored. This paper presents the first systematic investigation of MIA vulnerabilities in DLMs. Unlike the autoregressive models' single fixed prediction pattern, DLMs' multiple maskable configurations exponentially increase attack opportunities. This ability to probe many independent masks dramatically improves detection chances. To exploit this, we introduce SAMA (Subset-Aggregated Membership Attack), which addresses the sparse signal challenge through robust aggregation. SAMA samples masked subsets across progressive densities and applies sign-based statistics that remain effective despite heavy-tailed noise. Through inverse-weighted aggregation prioritizing sparse masks' cleaner signals, SAMA transforms sparse memorization detection into a robust voting mechanism. Experiments on nine datasets show SAMA achieves 30\% relative AUC improvement over the best baseline, with up to 8$\times$ improvement at low false positive rates. These findings reveal significant, previously unknown vulnerabilities in DLMs, necessitating the development of tailored privacy defenses.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 20589