Computer systems for detecting training data usage in generative models

US11366982B2 · kind B2 · utility

Assignee

• SAP SE · DE

Inventors

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

Key dates

• Filing date: Sep 24, 2018
• Grant date: Jun 21, 2022
• Expiry date: Apr 22, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N7/01
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Various examples are directed to systems and methods for detecting training data for a generative model. A computer system may access generative model sample data and a first test sample. The computer system may determine whether a first generative model sample of the plurality of generative model samples is within a threshold distance of the first test sample and whether a second generative model sample of the plurality of generative model samples is within the threshold distance of the first test sample. The computer system may determine that a probability that the generative model was trained with the first test sample is greater than or equal to a threshold probability based at least in part on whether the first generative model sample is within the threshold distance of the first test sample, the determining also based at least in part on whether the second generative model sample is within the threshold distance of the first test sample.