JUMP: Single-Pass Membership Inference Attack on Fine-Tuned Diffusion Language Models
A new attack method called JUMP is introduced for membership inference on fine-tuned discrete diffusion language models (dLLMs). By leveraging the models' any-order and parallel decodability, JUMP achieves higher ROC-AUC (0.90 vs 0.82) than previous methods like SAMA on LLaDA-8B-Base across six domains, while requiring fewer model queries. The approach uses a single-pass scoring strategy that jointly probes selected masked positions, improving both efficiency and detection performance.
Why it matters: This work reveals a significant privacy vulnerability in diffusion language models, demonstrating that membership inference can be performed more efficiently and accurately than previously known.
Full story at: arXiv AI/ML ↗