3min chapter

Ethical GPTs with Amruta Moktali

Machine Learning Archives - Software Engineering Daily

CHAPTER

How to Redact Sensitive Data

Some product offerings out there are essentially fully redacted or even replaced sensitive data was synthetic data before the training staff. You can't just completely redact the way we do reduction on Rn, right? You have to redact with the stand in. And what I mean by that is you redact information, but you still have to tell the model saying, you know what? There was a name here. So they're okay, both synthetic and reduction to a certain point, but it doesn't really help us get the power of LLMs," he says.

00:00