Patent · US Active

Interpretability framework for differentially private deep learning

US12001588B2 · kind B2 · utility

0Cited by

0References

7Claims

0Family size

Assignee

SAP SE · DE

Inventors

Daniel Bernau · Karlsruhe, DE
Philip-William Grassal · Heidelberg, DE
Hannah Keller · St. Petersburg, US
Martin Haerterich · Wiesloch, DE

Key dates

Filing date	Oct 30, 2020
Grant date	Jun 4, 2024
Priority date	—
Expiry date	Jun 4, 2042

Classification

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

Abstract

Data is received that specifies a bound for an adversarial posterior belief ρc that corresponds to a likelihood to re-identify data points from the dataset based on a differentially private function output. Privacy parameters ε, δ are then calculated based on the received data that govern a differential privacy (DP) algorithm to be applied to a function to be evaluated over a dataset. The calculating is based on a ratio of probabilities distributions of different observations, which are bound by the posterior belief ρc as applied to a dataset. The calculated privacy parameters are then used to apply the DP algorithm to the function over the dataset. Related apparatus, systems, techniques and articles are also described.

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