Patent · US Active

Measuring the vulnerability of AI modules to spoofing attempts

US11500998B2 · kind B2 · utility

0Cited by

1References

16Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Volker Fischer · Leonberg, DE
Jan Hendrik Metzen · Hessenhöfe, DE

Key dates

Filing date	Nov 22, 2019
Grant date	Nov 15, 2022
Priority date	—
Expiry date	Jan 29, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06V20/582
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method is described for measuring the vulnerability of an AI module to spoofing attempts, including the classification and/or regression onto which the AI module maps the update data set is ascertained as an unperturbed result for a predefined data set in the input space E; at least one perturbation S having a dimensionality d<D is applied to the predefined data set so that at least one perturbed data set results in the input space E; the classification and/or regression onto which the AI module maps the perturbed data set is ascertained as the perturbed result; the deviation of the perturbed result from the unperturbed result is ascertained using predefined metrics; in response to the deviation satisfying a predefined criterion, it is determined that the AI module with regard to the predefined data set is vulnerable to spoofing attempts having a dimensionality d.

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