Abtin Mahyar
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Crypto×1Databases×1
Frequent co-authors
Research Timeline
2026
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
The paper proposes FERMI, a method that significantly improves membership inference attacks against tabular diffusion models by leveraging auxiliary relational information available during training, even when only single-table features are visible at inference time.
Highlighted terms show continued research focus across papers