Jul 2026
From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
This work establishes a theoretical framework that proves that privacy leakage accumulates as more ODMM models are exposed, and proposes PRIME (Privacy Amplification RIsk from One-Dataset-Multiple-Model Exposure) to systematically assess this risk and quantify the resulting leakage using membership inference attacks (MIAs).
Qirui Huang, Na Li, Hong-Sheng Hu et al.
· arXiv.org · 0 citations