Active locking mechanism using machine learning
Methods and systems disclosed herein describe using machine learning to lock and unlock a device. Machine learning may be trained to recognize one or more features. Once the device has been trained to recognize one or more features, a user may define an unlock condition for the device using the one or more trained features. After defining the unlock condition, the device may be locked by verifying the one or more features that the user defined as the unlock condition using machine learning. When verification is successful, the device may be unlocked and the user allowed to access the device.
1. A method comprising:
receiving a request to unlock a portion of capabilities of a computing device;
receiving, via one or more inputs of the computing device, a first authentication parameter, wherein the first authentication parameter comprises a first background image captured as part of a request for biometric authentication;
determining, using one or more transceivers, a location of the computing device;
determining that the first background image matches a second background image associated with the location of the computing device;
determining, based on the first background image matching the second background image, that an unlock condition has been satisfied;
deriving, based on a determination that the unlock condition has been satisfied, an encryption key; and
unlocking, based on a determination that the unlock condition has been satisfied, the portion of capabilities of the computing device, wherein the unlocking the portion of capabilities of the computing device comprises decrypting a storage device associated with the computing device using the encryption key.
2. The method of claim 1 , wherein the unlocking the portion of capabilities of the computing device comprises transitioning from a locked screen to an unlocked screen.
3. The method of claim 2 , wherein the unlocked screen comprises at least one of a graphical user interface or a desktop.
4. The method of claim 1 , further comprising:
deriving the encryption key based on the first background image.
5. The method of claim 1 , further comprising:
determining, based on the location of the computing device, the second background image.
6. The method of claim 1 , wherein the determining that the unlock condition has been satisfied is further based on a determination that a current time corresponds to a time range defined in the unlock condition.
7. The method of claim 1 , further comprising:
using a machine learning model trained to recognize one or more environmental features to determine that the first background image matches the second background image.
8. The method of claim 1 , wherein the determining that the first background image matches the second background image associated with the location of the computing device comprises:
generating a first feature vector for the first background image; and
comparing the first feature vector to a baseline feature vector associated with the second background image, wherein a determination that the first background image matches the second background image is based on the first feature vector matching the baseline feature vector.
9. A computing device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the computing device to:
receive a request to unlock a portion of capabilities of the computing device;
receive, via one or more inputs of the computing device, a first authentication parameter, wherein the first authentication parameter comprises a first background image captured as part of a request for biometric authentication;
determine, using one or more transceivers, a location of the computing device;
determine that the first background image matches a second background image associated with the location of the computing device;
determine, based on the first background image matching the second background image, that an unlock condition has been satisfied;
derive, based on a determination that the unlock condition has been satisfied, an encryption key; and
unlock, based on a determination that the unlock condition has been satisfied, the portion of capabilities of the computing device, wherein unlocking the portion of capabilities of the computing device comprises decrypting a storage device associated with the computing device using the encryption key.
10. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to:
transition from a locked screen to an unlocked screen as part of unlocking the portion of capabilities of the computing device.
11. The computing device of claim 10 , wherein the unlocked screen comprises at least one of a graphical user interface or a desktop.
12. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to:
derive the encryption key based on the first background image.
13. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to:
determine, based on the location of the computing device, the second background image.
14. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to determine that the unlock condition has been satisfied further based on a determination that a current time corresponds to a time range defined in the unlock condition.
15. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to:
use a machine learning model trained to recognize one or more environmental features to determine that the first background image matches the second background image.
16. The computing device of claim 9 , wherein the instructions that, when executed by the one or more processors, cause the computing device to determine that the first background image matches the second background image associated with the location of the computing device by:
generating a first feature vector for the first background image; and
comparing the first feature vector to a baseline feature vector associated with the second background image, wherein a determination that the first background image matches the second background image is based on the first feature vector matching the baseline feature vector.
17. A non-transitory computer-readable medium comprising instructions that, when executed, configure a computing device to:
receive a request to unlock a portion of capabilities of the computing device;
receive, via one or more inputs of the computing device, a first authentication parameter, wherein the first authentication parameter comprises a first background image captured as part of a request for biometric authentication;
determine, using one or more transceivers, a location of the computing device;
determine that the first background image matches a second background image associated with the location of the computing device;
determine, based on the first background image matching the second background image, that an unlock condition has been satisfied;
derive, based on a determination that the unlock condition has been satisfied, an encryption key; and
unlock, based on a determination that the unlock condition has been satisfied, the portion of capabilities of the computing device, wherein unlocking the portion of capabilities of the computing device comprises decrypting a storage device associated with the computing device using the encryption key.
18. The non-transitory computer-readable medium of claim 17 , wherein the instructions that, when executed, configure the computing device to:
transition from a locked screen to an unlocked screen as part of unlocking the portion of capabilities of the computing device.
19. The non-transitory computer-readable medium of claim 18 , wherein the unlocked screen comprises at least one of a graphical user interface or a desktop.
20. The non-transitory computer-readable medium of claim 18 , wherein the instructions that, when executed, configure the computing device to:
derive the encryption key based on the first background image.
21. The non-transitory computer-readable medium of claim 17 , wherein the instructions that, when executed, configure the computing device to:
determine, based on the location of the computing device, the second background image.
22. The non-transitory computer-readable medium of claim 17 , wherein the instructions that, when executed, configure the computing device to determine that the unlock condition has been satisfied further based on a determination that a current time corresponds to a time range defined in the unlock condition.
23. The non-transitory computer-readable medium of claim 17 , wherein the instructions that, when executed, configure the computing device to:
use a machine learning model trained to recognize one or more environmental features to determine that the first background image matches the second background image.
24. The non-transitory computer-readable medium of claim 17 , wherein the instructions that, when executed, configure the computing device to determine that the first background image matches the second background image associated with the location of the computing device by:
generating a first feature vector for the first background image; and
comparing the first feature vector to a baseline feature vector associated with the second background image, wherein a determination that the first background image matches the second background image is based on the first feature vector matching the baseline feature vector.