Mixing Real and T2I Synthetic Data Can Amplify Privacy Risks, Study Finds

Jul 16, 2026

A new preprint demonstrates that combining real and text-to-image (T2I) synthetic data for model training can increase privacy leakage of real samples, contrary to common assumptions. The authors introduce a theoretical framework explaining how synthetic data can force models to memorize real data more, and present RSMixLeak, a method to assess this risk using membership inference attacks. They also propose a lightweight indicator to help identify datasets at high risk for privacy leakage when used in mixed training.

Why it matters: This work reveals that synthetic data augmentation can unintentionally worsen privacy risks for real data, challenging prevailing practices in privacy-preserving AI training.

Full story at: arXiv Cryptography and Security ↗