Security & Privacy
Differential privacy
A mathematical way to limit how much a shared result can reveal about any one person's participation.
Example
An organization adds carefully controlled randomness to shared statistics.
Why people use it
It limits how much a published analysis can reveal about one person's participation.
What you'll hear
“How much could this result reveal about one individual?”
What this means for you
Ask what privacy protection is promised and how it affects the usefulness of the figures.
Can you control it?
Developer-only
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does differential privacy mean the result is perfectly exact and reveals nothing?
- No. It provides a quantified privacy guarantee with a utility tradeoff.
- Can stronger protection reduce detail?
- Yes. Limiting what can be inferred can make the released result less precise or useful.
- Does it simply mean removing names?
- No. It is a mathematical approach to limiting information leakage, not just deleting obvious identifiers.