Patent · US Active

Method for recognizing an adversarial disturbance in input data of a neural network

US12073329B2 · kind B2 · utility

0Cited by

0References

23Claims

0Family size

Assignee

VOLKSWAGEN AKTIENGESELLSCHAFT · DE

Inventors

Nikhil Kapoor · Wolfsburg, DE
Peter Schlicht · Wolfsburg, DE
John Serin Varghese · Braunschweig, DE

Key dates

Filing date	Aug 6, 2020
Grant date	Aug 27, 2024
Priority date	—
Expiry date	Aug 3, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/094
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbations conditioned on input data of the neural network, and wherein a discriminator network of the conditional generative adversarial network is trained at least to detect an adversarial perturbation in the input data generated by the generator network, and wherein, during an application phase, the trained discriminator network detects an adversarial perturbation in input data of the neural network and provides a detection result. Also disclosed is a backend server, a detection device and a system.

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