Patent · US Active

Differential privacy to prevent machine learning model membership inference

US11449639B2 · kind B2 · utility

1Cited by

0References

20Claims

0Family size

Assignee

SAP SE · DE

Inventors

Daniel Bernau · Karlsruhe, DE
Jonas Robl · Heidelberg, DE
Philip-William Grassal · Heidelberg, DE
Florian Kerschbaum · Walldorf, DE

Key dates

Filing date	Jun 14, 2019
Grant date	Sep 20, 2022
Priority date	—
Expiry date	Apr 8, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N20/00
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Machine learning model data privacy can be maintained by training a machine learning model forming part of a data science process using data anonymized using each of two or more differential privacy mechanisms. Thereafter, it is determined, for each of the two or more differential privacy mechanisms, a level of accuracy and a level precision when evaluating data with known classifications. Subsequently, using the respective determined levels of precision and accuracy, a mitigation efficiency ratio is determined for each of the two or more differential privacy mechanisms. The differential privacy mechanism having a highest mitigation efficiency ratio is then incorporated into the data science process. Related apparatus, systems, techniques and articles are also described.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.