AI RESEARCH
Privacy Auditing Synthetic Data Release through Local Likelihood Attacks
arXiv CS.LG
•
ArXi:2508.21146v2 Announce Type: replace Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely on heuristics and unrealistic assumptions about model access, offering limited ability to describe or detect the privacy exposure of