Differential Privacy (DP) is commonly cited as a powerful Privacy Enhancing Technology (PET) that provides mathematical privacy guarantees to protect and secure private or personal data. Due to growing concerns – including actual attacks aimed at soliciting or extracting personal data from AI models – various forms of DP have been proposed to provide or achieve a sufficient level of anonymisation during the Machine Learning (ML) stage of AI model development.
In this webinar, you will learn about the core concepts of how DP has been applied to ML, without getting bogged down in overly complex technical or mathematical explanations, while gaining more practical clarity beyond the typical “just add noise to the data”.
If you would like to explore courses from our Academy on Data Protection, Cyber Regulation & AI Governance, please click here.
For courses on Privacy Engineering, Cybersecurity & AI Technology, please click here.