Encryption using biometric image-based key
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;
convert the image of the biometric identifier of the user into a key by:
using a neural network, wherein the key is a mathematical representation;
inputting the image of the biometric identifier 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 of the biometric identifier of the user in response to converting of the image into the key using the neural network.
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 instructions, when executed by the processor, further cause the processor to:
convert the image of the biometric identifier of the user into the key by inputting the image of the biometric identifier of the user into a trained neural network.
4. The system of claim 3 , wherein the instructions, when executed by the processor, further cause the processor to:
receive a set of generic biometric images that does not include the image of the biometric identifier of the user; and
train a neural network on the set of generic biometric images to yield the trained neural network.
5. The system of claim 1 , wherein the image of the biometric identifier of the user 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 of the biometric identifier into a second key;
use the second key to attempt to decrypt the encrypted data; and
discard the second image of the biometric identifier.
6. The system of claim 5 , wherein the instructions, when executed by the processor, further cause the processor to:
convert the second image of the biometric identifier into the second key by inputting the second image of the biometric identifier into a trained neural network.