Differential Privacy

A mathematical framework providing formal privacy guarantees by adding calibrated noise to data or computations, ensuring that the output of an analysis does not significantly change when any single individual's data is included or excluded.

Adding a small amount of random noise to data or results so you can analyse trends without exposing any individual's information. Like a survey that adds random fuzz so no single response can be identified.

Differential privacy is a key technical control for meeting data protection requirements in your AI governance framework. It enables your organisation to derive insights from sensitive data while providing mathematical privacy guarantees.