Patents by Inventor Ngoc Minh Tran

Ngoc Minh Tran 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: 20210312336
    Abstract: Embodiments for providing optimized machine learning model features using federated learning on distributed data in a computing environment by a processor. Machine learning model features may be learned from one or more data sets extracted from one or more localized machine learning models associated with one or more nodes. The machine learning model features may be aggregated using a centralized machine learning model at a source node. The one or more localized machine learning models may be trained using aggregated machine learning model features provided by the centralized machine learning model.
    Type: Application
    Filed: April 3, 2020
    Publication date: October 7, 2021
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Mathieu SINN, Ngoc Minh TRAN, Stefano BRAGHIN, Mark PURCELL
  • Patent number: 11087525
    Abstract: Embodiments for intelligent unsupervised learning of visual alphabets by one or more processors are described. A visual three-dimensional (3D) alphabet may be learned from one or more images using a machine learning operations. A set of 3D primitives representing the visual 3D alphabet may be provided.
    Type: Grant
    Filed: January 8, 2020
    Date of Patent: August 10, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Thanh Lam Hoang, Albert Akhriev, Ngoc Minh Tran, Bradley Eck, Tuan Dinh
  • Publication number: 20210209833
    Abstract: Embodiments for intelligent unsupervised learning of visual alphabets by one or more processors are described. A visual three-dimensional (3D) alphabet may be learned from one or more images using a machine learning operations. A set of 3D primitives representing the visual 3D alphabet may be provided.
    Type: Application
    Filed: January 8, 2020
    Publication date: July 8, 2021
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Thanh Lam HOANG, Albert AKHRIEV, Ngoc Minh TRAN, Bradley ECK, Tuan DINH
  • Patent number: 11036857
    Abstract: A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example.
    Type: Grant
    Filed: November 15, 2018
    Date of Patent: June 15, 2021
    Assignee: International Business Machines Corporation
    Inventors: Ngoc Minh Tran, Mathieu Sinn, Ambrish Rawat, Maria-Irina Nicolae, Martin Wistuba
  • Publication number: 20210110071
    Abstract: Embodiments for providing adversarial protection to computing display devices by a processor. Security defenses may be provided on one or more image display devices against automated media analysis by using adversarial noise, an adversarial patch, or a combination thereof.
    Type: Application
    Filed: October 14, 2019
    Publication date: April 15, 2021
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat BUESSER, Maria-Irina NICOLAE, Ambrish RAWAT, Mathieu SINN, Ngoc Minh TRAN, Martin WISTUBA
  • Publication number: 20210110045
    Abstract: Various embodiments are provided for securing trained machine learning models by one or more processors in a computing system. One or more hardened machine learning models are secured against adversarial attacks by adding adversarial protection to one or more trained machine learning model.
    Type: Application
    Filed: October 14, 2019
    Publication date: April 15, 2021
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat BUESSER, Maria-Irina NICOLAE, Ambrish RAWAT, Mathieu SINN, Ngoc Minh TRAN, Martin WISTUBA
  • Publication number: 20210073376
    Abstract: Various embodiments are provided for securing machine learning models by one or more processors in a computing system. One or more hardened machine learning models that are secured against adversarial attacks are provided by applying one or more of a plurality of combinations of selected preprocessing operations from one or more machine learning models, a data set used for hardening the one or more machine learning models, a list of preprocessors, and a selected number of learners.
    Type: Application
    Filed: September 10, 2019
    Publication date: March 11, 2021
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ngoc Minh TRAN, Mathieu SINN, Maria-Irina NICOLAE, Martin WISTUBA, Ambrish RAWAT, Beat BUESSER
  • Patent number: 10896664
    Abstract: Embodiments for providing adversarial protection of speech in audio signals by a processor. Security defenses on one or more audio devices may be provide against automated audio analysis of audio signals by using adversarial noise.
    Type: Grant
    Filed: October 14, 2019
    Date of Patent: January 19, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat Buesser, Maria-Irina Nicolae, Ambrish Rawat, Mathieu Sinn, Ngoc Minh Tran, Martin Wistuba
  • Publication number: 20200380017
    Abstract: Embodiments for automatic feature learning for predictive modeling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.
    Type: Application
    Filed: August 25, 2020
    Publication date: December 3, 2020
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat BUESSER, Thanh Lam HOANG, Mathieu SINN, Ngoc Minh TRAN
  • Patent number: 10839249
    Abstract: Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.
    Type: Grant
    Filed: March 8, 2019
    Date of Patent: November 17, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Thanh Lam Hoang, Beat Buesser, Ngoc Minh Tran, Charles Jochim
  • Publication number: 20200285885
    Abstract: Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.
    Type: Application
    Filed: March 8, 2019
    Publication date: September 10, 2020
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Thanh Lam HOANG, Beat BUESSER, Ngoc Minh TRAN, Charles JOCHIM
  • Patent number: 10762111
    Abstract: Embodiments for automatic feature learning for predictive modelling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.
    Type: Grant
    Filed: September 25, 2017
    Date of Patent: September 1, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat Buesser, Thanh Lam Hoang, Mathieu Sinn, Ngoc Minh Tran
  • Publication number: 20200159924
    Abstract: A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example.
    Type: Application
    Filed: November 15, 2018
    Publication date: May 21, 2020
    Inventors: Ngoc Minh Tran, Mathieu Sinn, Ambrish Rawat, Maria-Irina Nicolae, Martin Wistuba
  • Publication number: 20190354849
    Abstract: Embodiments for automatic data preprocessing for a machine learning operation by a processor. For each data instance in a set of data instances, a sequence of actions may be automatically learned in a reinforcement learning environment to be applied for preprocessing each data instance separately.
    Type: Application
    Filed: May 17, 2018
    Publication date: November 21, 2019
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ngoc Minh TRAN, Mathieu SINN, Thanh Lam HOANG, Martin WISTUBA
  • Publication number: 20190095515
    Abstract: Embodiments for automatic feature learning for predictive modelling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.
    Type: Application
    Filed: September 25, 2017
    Publication date: March 28, 2019
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Beat BUESSER, Thanh Lam HOANG, Mathieu SINN, Ngoc Minh TRAN
  • Patent number: 5751579
    Abstract: A vehicle traction control system is controlled in-part by a signal value indicative of estimated wheel torque. The estimated wheel torque value is produced within the vehicle's electronic engine control (EEC) module by summing a first value which indicated the estimated torque attributable to engine combustion and a second value which is proportional to engine acceleration/deceleration which indicates the amount of torque attributable to the inertial movement of engine and drive train masses. Before summing the two signal components, the signal which indicates combustion torque is delayed with respect to the signal indicating inertial torque by a delay interval whose duration varies with engine speed to take into account the delay between intake fuel rate changes and combustion forces as well as delays attributable to the timing of the calculations themselves.
    Type: Grant
    Filed: September 6, 1995
    Date of Patent: May 12, 1998
    Assignee: Ford Global Technologies, Inc.
    Inventors: Davorin David Hrovat, Daniel Scott Colvin, Michael Alan Weyburne, Ngoc Minh Tran, John Loring Yester