Differential privacy is a privacy-preserving framework that limits what can be inferred about any individual from the output of a computation or model. It commonly uses techniques such as sampling and controlled noise addition to reduce the risk that sensitive training or analysis data can be exposed.
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.