Encryption using biometric image-based key
View Patent ↗Methods and systems according to the present disclosure improve upon known biometric security systems by not permanently storing (e.g., for later comparison as in known systems) the actual image of the biometric characteristic. Instead, an image of a biometric identifier (e.g., retina, fingerprint, etc.) may be used to form a key which may be used to secure and provide access to data. The key may be formed, in embodiments, using a neural network and/or a random input (e.g., a vector of random characters), for example. The image of the biometric identifier may be discarded, and thus may not be vulnerable to theft. In an embodiment, the key may be used in a key-based encryption system.
1. A system comprising:
a processor; and
a non-transitory computer-readable memory storing instructions that, when executed by the processor, cause the processor to:
receive an image of a biometric identifier of a user;
receive a set of generic biometric images that does not include the image of the biometric identifier of the user;
train a neural network on the set of generic biometric images to yield a trained neural network;
convert the image into a key by:
transforming the image into an image data matrix;
combining the image data matrix with a randomized initialization matrix to create the key; and
converting the image into the key by inputting the image into the trained neural network;
use the key to encrypt data to create encrypted data; and
discard the image of the biometric identifier and the image data matrix.
2. The system of claim 1 , wherein the instructions, when executed by the processor, further cause the processor to:
discard the key.
3. The system of claim 1 , wherein the image of the biometric identifier is a first image and the key is a first key, further wherein the instructions, when executed by the processor, further cause the processor to:
receive a second image of a biometric identifier;
convert the second image into a second key;
use the second key to attempt to decrypt the encrypted data; and
discard the second image.
4. The system of claim 3 , wherein the instructions, when executed by the processor, further cause the processor to:
convert the second image into the second key by inputting the second image into a trained neural network.
5. The system of claim 1 , wherein the instructions, when executed by the processor, further cause the processor to:
convert the image into the key by:
inputting the image into an image processing algorithm to yield an image data matrix;
applying a one-way function to the image data matrix to yield a secure image data matrix; and
combining the secure image data matrix with a randomized initialization matrix to create the key; and
discard the image data matrix and the secure image data matrix.
6. The system of claim 5 , wherein the one-way function comprises a cryptographic hash function.
7. The system of claim 5 , wherein the image data matrix is a vector.
8. A method comprising:
receiving an image of a biometric identifier of a user;
receiving a set of generic biometric images that does not include the image of the biometric identifier of the user;
training a neural network on the set of generic biometric images to yield a trained neural network;
converting the image into a key by:
inputting the image into the trained neural network;
transforming, with a computer, the image into an image data matrix;
applying a one-way function to the image data matrix to yield a secure image data matrix; and
combining the secure image data matrix with a randomized initialization matrix to create the key;
using the key to encrypt data to create encrypted data; and
discarding the image of the biometric identifier, the image data matrix, and the secure image data matrix.
9. The method of claim 8 , further comprising:
discarding the key.
10. The method of claim 8 , wherein the image of the biometric identifier is a first image and the key is a first key, the method further comprising:
receiving a second image of a biometric identifier;
converting the second image into a second key;
using the second key to attempt to decrypt the encrypted data; and
discarding the second image.
11. The method of claim 10 , further comprising:
converting the second image into the second key by inputting the second image into a trained neural network.
12. The method of claim 8 , further comprising:
converting the image into the key by:
inputting the image into an image processing algorithm to yield an image data matrix; and
combining the image data matrix with a randomized initialization matrix to create the key; and
discarding the image data matrix.
13. The method of claim 8 , wherein the one-way function comprises a cryptographic hash function.
14. The method of claim 8 , wherein the image data matrix is a vector.