Electronic device and method for protecting electronic devices from being attack

Abstract

This invention provides an electronic device including an embedded controller. The embedded controller includes a key unit, a microcontroller unit, a detection unit, and an artificial intelligence unit. The key unit generates a key. The microcontroller unit performs encryption and decryption operations based on the first key generated by the key unit. The detection unit measures at least one parameter of the embedded controller. The artificial intelligence unit runs an artificial intelligence model to determine whether the at least one parameter is abnormal. When the artificial intelligence model determines that the at least one parameter is abnormal, the artificial intelligence unit performs at least one security operation.

Claims

1. An electronic device comprising: An embedded controller includes: a key unit for generating a key; a microcontroller unit for performing encryption and decryption operations based on a first key generated by the key unit; a detection unit for measuring at least one parameter of the embedded controller; and an artificial intelligence unit for running an artificial intelligence model to determine whether the at least one parameter is abnormal; wherein, when the artificial intelligence model determines that the at least one parameter is abnormal, the artificial intelligence unit performs at least one security operation.

2. The electronic device as described in claim 1, further comprising: A system bus connects to the embedded controller; and a peripheral bus connected to the embedded controller; wherein the detection unit includes: an analog-to-digital converter for measuring the at least one parameter; a system bus monitoring unit for collecting data transmitted on the system bus; and a peripheral bus monitoring unit for collecting data transmitted on the peripheral bus.

3. The electronic device as described in claim 1, wherein, The at least one security operation includes: controlling the key unit to generate a second key by the artificial intelligence unit; and controlling the microcontroller unit to perform encryption and decryption operations based on the second key by the artificial intelligence unit.

4. The electronic device as described in claim 1, wherein, The at least one safety operation includes: restarting the embedded controller via the artificial intelligence unit.

5. The electronic device as claimed in claim 1, wherein the microcontroller unit comprises: An encryption / decryption unit is used to perform encryption and decryption operations based on the first key; and a microcontroller for controlling the encryption / decryption unit; wherein the at least one security operation includes: making the encryption / decryption unit and the microcontroller inaccessible by means of the artificial intelligence unit.

6. The electronic device as described in claim 5, wherein, After the artificial intelligence unit makes the encryption / decryption unit and the microcontroller inaccessible: the detection unit is used to detect a sound; when the sound's voiceprint matches a preset voiceprint, the artificial intelligence unit is used to enable the encryption / decryption unit and the microcontroller to be accessed.

7. The electronic device as claimed in claim 1, wherein, When the artificial intelligence model determines that at least one parameter is not abnormal, the artificial intelligence unit adds the parameter to a training dataset and uses the training dataset to train the artificial intelligence model.

8. A method for protecting an electronic device from attack, performed by an electronic device, the method comprising: A key is generated using a key unit; A microcontroller unit performs encryption and decryption operations based on a first key generated by the key unit; a detection unit measures at least one parameter of an embedded controller; an artificial intelligence unit runs an artificial intelligence model; the artificial intelligence model determines whether the at least one parameter is abnormal; and when the artificial intelligence model determines that the at least one parameter is abnormal, the artificial intelligence unit performs at least one security operation.

9. The method as described in claim 8, further comprising: The at least one parameter is measured by an analog-to-digital converter of the detection unit; data transmitted on a system bus is collected by a system bus monitoring unit of the detection unit, wherein the system bus is connected to the embedded controller; and data transmitted on a peripheral bus is collected by a peripheral bus monitoring unit of the detection unit, wherein the peripheral bus is connected to the embedded controller.

10. The method as described in claim 8, wherein, The at least one security operation includes: controlling the key unit to generate a second key by the artificial intelligence unit; and controlling the microcontroller unit to perform encryption and decryption operations based on the second key by the artificial intelligence unit.

11. The method as described in claim 8, wherein, The at least one safety operation includes: restarting the embedded controller via the artificial intelligence unit.

12. The method as described in claim 8, wherein, The at least one security operation includes: using the artificial intelligence unit to make an encryption / decryption unit and a microcontroller in the microcontroller unit inaccessible.

13. The method as described in claim 12, wherein, After the artificial intelligence unit renders the encryption / decryption unit and the microcontroller inaccessible, the method further includes: detecting a sound by the detection unit; and when the sound's voiceprint matches a preset voiceprint, enabling the encryption / decryption unit and the microcontroller to be accessed by the artificial intelligence unit.

14. The method as described in claim 8, further comprising: When the artificial intelligence model determines that at least one parameter is not abnormal based on the parameter, the artificial intelligence unit adds the parameter to a training dataset and uses the training dataset to train the artificial intelligence model.

Images