I'm looking at the Apple differential privacy document here and it has the paragraph:

The noise injection step works as follows: After encoding the input as a vector using a hash function, each coordinate of the vector is then flipped (written as an incorrect value) with a probability of 1/(1 + 𝑒^𝜀/2), where 𝜀 is the privacy parameter. This assures that analysis of the collected data cannot distinguish actual values from flipped values, helping to assure the privacy of the shared information.

I would like to experiment with hashing/obscuring my data with similar properties and have data bins that would look like this, but for different types of data.

enter image description here

How would I implement (or emulate) either the Count Mean Sketch or Hadamard Count Mean Sketch for my own purposes?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.