ε-PrivateSMOTE

ε-PrivateSMOTE is a technique designed for safeguarding against re-identification and linkage attacks, particularly addressing cases with a high re-identification risk. It generates synthetic data via noise-induced interpolation with differential privacy principles to obfuscate high-risk cases. ε-PrivateSMOTE allows having new cases similar to the originals while preserving privacy and maximising predictive utility. Most importanly, ε-PrivateSMOTE is a resource efficient and less time-consuming than conventional de-identification approaches such as deep learning and differential privacy-based solutions.