Patent · US Active

Accurately identifying members of training data in variational autoencoders by reconstruction error

US11501172B2 · kind B2 · utility

1Cited by

1References

15Claims

0Family size

Assignee

SAP SE · DE

Inventors

Benjamin Hilprecht · Mannheim, DE
Daniel Bernau · Karlsruhe, DE
Martin Haerterich · Wiesloch, DE

Key dates

Filing date	Dec 13, 2018
Grant date	Nov 15, 2022
Priority date	—
Expiry date	Apr 12, 2040

Classification

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

Abstract

A system is described that can include a machine learning model and at least one programmable processor communicatively coupled to the machine learning model. The machine learning model can receive data, generate a continuous probability distribution associated with the data, sample a latent variable from the continuous probability distribution to generate a plurality of samples, and generate reconstructed data from the plurality of samples. The at least one programmable processor can compute a reconstruction error by determining a distance between the reconstructed data and the data, and generate, based on the reconstruction error, an indication representing whether a specific record within the received data was used to train the machine learning model. Related apparatuses, methods, techniques, non-transitory computer programmable products, non-transitory machine-readable medium, articles, and other systems are also within the scope of this disclosure.

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