Patents by Inventor Luca Bertinetto

Luca Bertinetto 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).

  • Publication number: 20250131281
    Abstract: A computer-implemented method of generating black-box adversarial inputs to a perception component using a surrogate model of the perception component comprises receiving an initial input to the perception component and repeatedly perturbing the initial input until an adversarial input is found that satisfies an attack objective by: performing a primary attack process by perturbing the initial input based on a computed gradient of a surrogate attack loss function of the surrogate model that encodes the attack objective; wherein, if the primary attack process terminates without finding any perturbed input satisfying the promising attack condition, a backup attack process is performed to perform a randomized search of the input space of the perception component, guided by the surrogate model, until a perturbed input satisfying the promising attack condition is found; wherein the primary attack process is repeated based on the perturbed input found by the primary attack process or backup process.
    Type: Application
    Filed: September 26, 2022
    Publication date: April 24, 2025
    Applicant: Five AI Limited
    Inventors: Nicholas A. Lord, Luca Bertinetto, Romain Mueller
  • Publication number: 20250037441
    Abstract: The problem of domain shift error in computer vision models and other perception components is addressed. In a label approximation phase, an approximate label distribution is computed for each input of a target batch using a trained machine learning (ML) perception component. In an online label optimization phase, a modified label distribution is assigned to each input of the target batch, via optimization of an unsupervised loss function that (i) penalizes divergence between the approximate label distribution and the modified label distribution for each input of the target batch (ii) penalizes deviation between the modified label distributions assigned to input pairs of the target batch having similar features.
    Type: Application
    Filed: November 15, 2022
    Publication date: January 30, 2025
    Applicant: Five AI Limited
    Inventors: Malik Boudiaf, Luca Bertinetto
  • Publication number: 20240370572
    Abstract: A computer-implemented method of generating black-box adversarial inputs to a perception component comprises computing an adversarial input by applying a perturbation to an original input, the adversarial input satisfying an attack objective when inputted to the perception component. The perturbation is determined by selectively combining component perturbations selected from a predetermined set of component perturbations. Inputs correspond to respective points in an input vector space, and the component perturbations encode principal attack directions in the input vector space for satisfying said attack objective, the principal attack directions having been determined by analyzing: (i) a set of sample attack directions, or (ii) a set of input samples.
    Type: Application
    Filed: May 19, 2022
    Publication date: November 7, 2024
    Applicant: Five AI Limited
    Inventors: Nicholas A Lord, Luca Bertinetto, Romain Mueller
  • Patent number: 12019714
    Abstract: A perception model is trained to classify inputs in relation to a discrete set of leaf node classes. A hierarchical classification tree encodes hierarchical relationships between the leaf node classes. A training loss function is dependent on a classification score for a given training input a its ground truth leaf node class of the training input, but also classification scores for at least some others of the leaf node classes, with the classification scores of the other leaf node classes weighted in dependence on their hierarchical relationship to the ground truth leaf node class within the hierarchical classification tree.
    Type: Grant
    Filed: November 13, 2020
    Date of Patent: June 25, 2024
    Assignee: Five AI Limited
    Inventors: Luca Bertinetto, Romain Mueller, Konstantinos Tertikas, Sina Samangooei, Nicholas A Lord
  • Publication number: 20210150346
    Abstract: A perception model is trained to classify inputs in relation to a discrete set of leaf node classes. A hierarchical classification tree encodes hierarchical relationships between the leaf node classes. A training loss function is dependent on a classification score for a given training input a its ground truth leaf node class of the training input, but also classification scores for at least some others of the leaf node classes, with the classification scores of the other leaf node classes weighted in dependence on their hierarchical relationship to the ground truth leaf node class within the hierarchical classification tree.
    Type: Application
    Filed: November 13, 2020
    Publication date: May 20, 2021
    Applicant: Five AI Limited
    Inventors: Luca Bertinetto, Romain Mueller, Konstantinos Tertikas, Sina Samangooei, Nicholas A. Lord