Methods and apparatuses for detecting tamper using machine learning models
AssigneeCACI, Inc.—Federal
InventorsJames Andrew Cook, Brian Andrew Rowe, Eric David Nystrom
Life of this patent
Estimating the term…
Abstract
The present application describes a machine learning method for detecting tamper. The method includes a step of training a model using one or more values obtained from one or more different sensors on an integrated module. The one or more values act as training data with respect to one or more of light, acceleration, magnetic field, rotation, temperature, pressure, humidity, and audio. The method also includes a step of predicting, via the trained model, tampering of the of the integrated module. The present application also describes a system for detecting tamper.
Claims20
A machine learning method comprising:
- training a model using one or more values obtained from one or more different sensors on an integrated module, the one or more values acting as training data with respect to one or more of light, acceleration, magnetic field, rotation, temperature, pressure, humidity, and audio;
- and
- predicting, via the trained model, tampering of the of the integrated module.
A method comprising:
- training a machine learning model for detecting a tamper event using one or more values obtained from a plurality of different sensors on an integrated chip, the one or more values acting as training data with respect to one or more of light, acceleration, magnetic field, rotation, temperature, pressure, humidity, and audio;
- obtaining one or more other values from the one or more sensors;
- further training the machine learning model using the one or more other values;
- and
- predicting the tamper event using the further-trained machine learning model.
A system comprising
- a non-transitory memory;
- and
- a processor coupled to the memory and configured to execute instructions of:
- training a model using one or more values obtained from one or more different sensors on an integrated module, the one or more values acting as training data with respect to one or more of light, acceleration, magnetic field, rotation, temperature, pressure, humidity, and audio;
- and
- predicting, via the trained model, tampering of the of the integrated module.
Dependencies are inferred from the claim text.