You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
regarding the delta-presence privacy metric, the Docs state:
"Returns the maximum re-identification probability on the real dataset from the synthetic dataset.
For each dataset partition, we report the maximum ratio of unique sensitive information between the real dataset and in the synthetic dataset."
However, the delta_presence method does not require inputting the Sensitive Attributes and generally delta-presence relies on the comparison with a public dataset.
It would be great to have a paper reference, to know how sensitive attributes are chosen and what is the public dataset that this algo refers to.
Thank you for the excellent work.
The text was updated successfully, but these errors were encountered:
Hi,
regarding the delta-presence privacy metric, the Docs state:
"Returns the maximum re-identification probability on the real dataset from the synthetic dataset.
For each dataset partition, we report the maximum ratio of unique sensitive information between the real dataset and in the synthetic dataset."
However, the delta_presence method does not require inputting the Sensitive Attributes and generally delta-presence relies on the comparison with a public dataset.
It would be great to have a paper reference, to know how sensitive attributes are chosen and what is the public dataset that this algo refers to.
Thank you for the excellent work.
The text was updated successfully, but these errors were encountered: