La privacidad diferencial es un marco de preservación de la privacidad que limita lo que puede inferirse sobre cualquier individuo a partir de la salida de un cálculo o modelo. Comúnmente utiliza técnicas como muestreo y adición controlada de ruido para reducir el riesgo de exposición de datos sensibles de entrenamiento o análisis.
In machine learning, an anonymization approach to protect any sensitive data (for example, an individual's personal information) included in a model's training set from being exposed. This approach ensures that the model doesn't learn or remember much about a specific individual. This is accomplished by sampling and adding noise during model training to obscure individual data points, mitigating the risk of exposing sensitive training data. Differential privacy is also used outside of machine learning. For example, data scientists sometimes use differential privacy to protect individual privacy when computing product usage statistics for different demographics.