Session Outline
How should we think about data governance in the new Generative AI reality? First, good news. Data professionals can leverage existing data privacy and governance principles and tools to address the challenges posed by generative AI. Over the last two decades, Inna has worked as a technical leader in the data domain. She has experienced the importance of balancing the collection of valuable data with personal privacy protection.
From her talk at the Data Innovation Summit 2024, you will learn how to use anonymization to remove personally identifiable information from data. How to use deliberate data decay to ensure that data does not remain accessible for longer than necessary. And how to use differential privacy to add noise to data without compromising its accuracy. Then, we explore the differences in the new Generative AI world, and conclude 3 key principles for protecting user data in AI systems:
- Bring the model to the data;
- Sandbox the LLM;
- Control LLM access.
By the end of the talk, you will understand privacy and data governance challenges: both common and unique to AI. You will learn practical solutions for developing and implementing data privacy and governance practices. These practices support the responsible development and use of generative AI.