Skip to content

BEPIS is an experimental approach on realizing Epsilon-Differential-Privacy as data anonymization technique for graph database, e.g. Neo4j.

Notifications You must be signed in to change notification settings

Singheskan/BEPIS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Author: Patrick Singh

BEPIS - Description:

BEPIS is an experimental approach on realizing Epsilon-Differential-Privacy as data anonymization technique for graph database, e.g. Neo4j. It provides a console interface to a running Neo4j-Graph instance and ways to laod data into the system, as .csv files. Furthermore, it provides ways to query the database and translates these queries to queries enforcing epsilon-differential-privacy.

It provides experimental, first-steps into this topic and is therefore just providing a translation for aggregation queries, like counting queries. We are implementing the sensitivity-based mechanism with elastic sensitivity as an upper boundary to local sensitivity. Concretely, we are applying a smoothing function on top of local sensitivity to ensure a certain distance to the true database.

About

BEPIS is an experimental approach on realizing Epsilon-Differential-Privacy as data anonymization technique for graph database, e.g. Neo4j.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages