Patents by Inventor Florens Fabian Gressner

Florens Fabian Gressner has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Method and generator for generating disturbed input data for a neural network
    Patent number: 12322189
    Abstract: The invention relates to a method for generating disturbed input data for a neural network for analyzing sensor data, in particular digital images, of a driver assistance system, in which a first metric is defined which indicates how the magnitude of a change in sensor data is measured, a second metric is defined which indicates where a disturbance of sensor data is directed, an optimization problem is generated from a combination of the first metric and second metric, the optimization problem is solved by means of at least one solution algorithm, wherein the solution indicates a target disturbance of the input data, and disturbed input data is generated from sensor data for the neural network by means of the target disturbance.
    Type: Grant
    Filed: June 12, 2020
    Date of Patent: June 3, 2025
    Assignees: VOLKSWAGEN AKTIENGESELLSCHAFT, DSPACE GMBH
    Inventors: Fabian Hüger, Peter Schlicht, Nico Maurice Schmidt, Feix Assion, Florens Fabian Gressner
  • Defense generator, method for preventing an attack on an AI unit, and computer-readable storage medium
    Patent number: 12153718
    Abstract: Adversarial attacks pose a threat to the functioning of AI systems. A defense generator for dynamically generating at least one AI defense module is provided. A core feature of the invention is that a distribution function is determined for model data. The invention is based on the assumption that the model data belong to a model manifold, or have a similar statistical behavior. Thus, it is possible to determine for an input data set whether the data of the input data set can be associated with an adversarial attack. This is the case, for example, if statistical anomalies are found in the input data set.
    Type: Grant
    Filed: October 13, 2020
    Date of Patent: November 26, 2024
    Assignee: Neurocat GmbH
    Inventors: Felix Assion, Florens Fabian Gressner, Frank Kretschmer, Stephan Hinze
  • Method for Providing an Explanation Dataset for an AI Module, Computer-Readable Storage Medium, Device and System
    Publication number: 20230025692
    Abstract: Explaining the decisions of AI modules to a user is difficult.
    Type: Application
    Filed: November 19, 2020
    Publication date: January 26, 2023
    Inventors: Felix Assion, Florens Fabian Gressner, Stephan Hinze, Frank Kretschmer, Benedikt Julius Wagner
  • Method and Generator for Generating Disturbed Input Data for a Neural Network
    Publication number: 20220358747
    Abstract: The invention relates to a method for generating disturbed input data for a neural network for analyzing sensor data, in particular digital images, of a driver assistance system, in which a first metric is defined which indicates how the magnitude of a change in sensor data is measured, a second metric is defined which indicates where a disturbance of sensor data is directed, an optimization problem is generated from a combination of the first metric and second metric, the optimization problem is solved by means of at least one solution algorithm, wherein the solution indicates a target disturbance of the input data, and disturbed input data is generated from sensor data for the neural network by means of the target disturbance.
    Type: Application
    Filed: June 12, 2020
    Publication date: November 10, 2022
    Applicants: Volkswagen Aktiengesellschaft, Neurocat GmbH
    Inventors: Fabian Hüger, Peter Schlicht, Nico Maurice Schmidt, Feix Assion, Florens Fabian Gressner