Security as a service for machine learning
AssigneeInternational Business Machines Corporation
InventorsMansura Habiba, Gokhan Sagirlar, Martin Wistuba
Life of this patent
Estimating the term…
Abstract
Embodiments are disclosed for a method. The method includes validating training data that is provided for training a machine learning model using ordinary differential equations. The method further includes generating pre-processed training data from the validated training data by generating encrypted training data from the validated training data using homomorphic encryption and generating random noise based on the validated training data. The method also includes training the machine learning model adversarially with the pre-processed training data.
Claims17
A system comprising:
- one or more computer processing circuits;
- and
- one or more computer-readable storage media storing program instructions which, when executed by the one or more computer processing circuits, are configured to cause the one or more computer processing circuits to perform a method comprising:
- validating, before training a machine learning model using a deep learning network, training data that is provided for training a machine learning model using ordinary differential equations;
- generating pre-processed training data from the validated training data by:
- generating encrypted training data from the validated training data using homomorphic encryption;
- and
- generating random noise based on the validated training data;
- and
- training the machine learning model adversarially with the pre-processed training data.
A computer-implemented method, comprising:
- validating, before training a machine learning model using a deep learning network, training data that is provided for training a machine learning model using ordinary differential equations;
- generating pre-processed training data from the validated training data by:
- generating encrypted training data from the validated training data using homomorphic encryption;
- and
- generating random noise based on the validated training data;
- and
- training the machine learning model adversarially with the pre-processed training data.
A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:
- validating, before training a machine learning model using a deep learning network, training data that is provided for training a machine learning model using ordinary differential equations;
- generating pre-processed training data from the validated training data by:
- generating encrypted training data from the validated training data using homomorphic encryption;
- and
- generating random noise based on the validated training data;
- generating a plurality of adversarial examples from the pre-processed training data;
- and
- training the machine learning model adversarially with the pre-processed training data and the plurality of adversarial examples.
Dependencies are inferred from the claim text.