works on
data augmentation 1membership inference attack 1model memorization 1privacy 1synthetic data 1text-to-image generation 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CR2026

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

Na Li, Boyu Kuang, Hongsheng Hu +4

The paper shows that mixing text‑to‑image synthetic data with real data during training can increase privacy leakage of the real samples, and introduces a method (RSMixLeak) to mea…