Systems and methods for privacy-enabled biometric processing
A set of distance measurable encrypted feature vectors can be derived from any biometric data and/or physical or logical user behavioral data, and then using an associated deep neural network (“DNN”) on the output (i.e., biometric feature vector and/or behavioral feature vectors, etc.) an authentication system can determine matches or execute searches on encrypted data. Behavioral or biometric encrypted feature vectors can be stored and/or used in conjunction with respective classifications, or in subsequent comparisons without fear of compromising the original data. In various embodiments, the original behavioral and/or biometric data is discarded responsive to generating the encrypted vectors. In another embodiment, distance measurable or homomorphic encryption enables computations and comparisons on cypher-text without decryption of the encrypted feature vectors. Security of such privacy enabled embeddings can be increased by implementing an assurance factor (e.g., liveness) to establish a submitted credential has not been spoofed or faked.
1. A privacy-enabled authentication system comprising:
at least one processor operatively connected to a memory, the at least one processor configured to:
execute selection from a first machine learning (“ML”) process and a second ML process responsive to an authentication mode;
wherein the first ML process when executed by the at least one processor is configured to:
classify distance measurable encrypted feature vector inputs as part of identification or authentication using one or more first classification neural networks trained to predict matches to a plurality of identification classes for a respective distance measurable encrypted feature vector input;
wherein the second ML process when executed by the at least one processor is configured to:
accept plain text biometric or behavioral data as input to one or more generation neural networks and output respective distance measurable encrypted feature vectors;
generate an identification match based on comparing distances between distance measurable encrypted feature vectors; and
validate that identification results produced by the selected first and second ML processes are based on live submission from a live user, the validation including operations to determine liveness in multiple dimensions including at least a liveness evaluation of identification or authentication inputs of a matching type submitted to the selected first and second ML process during the identification or authentication as part of the evaluation of the multiple dimensions.
2. The system of claim 1 , wherein the first ML process when executed by the at least one processor is configured to accept distance measurable encrypted feature vector and label inputs during training of one or more first classification neural networks to define the plurality of identification classes.
3. The system of claim 1 , wherein one of the first ML process or the second ML process is configured to:
determine one or more distances between encrypted feature vectors produced by respective generation neural networks;
exclude encrypted feature vectors produced by respective generation neural networks having one or more distances exceeding a threshold distance from subsequent training processes; and
include encrypted feature vectors having distances within the threshold distance for subsequent training processes.
4. The system of claim 3 , wherein the at least one processor is configured to determine the authentication mode includes an enrollment mode for establishing a new entity for subsequent authentication.
5. The system of claim 4 , wherein the at least one processor is configured to trigger at least the second ML process responsive to determining a current authentication mode includes the enrollment mode.
6. The system of claim 4 , wherein the at least one processor is configured to trigger at least training operations of both the first and second ML processes responsive to determining that the current authentication mode includes the enrollment mode.
7. The system of claim 6 , wherein the at least one processor is configured to execute at least the second ML process to authenticate the new user until at least a period of time required for training the one or more first classification neural networks expires.
8. The system of claim 6 , wherein the at least one processor is configured to execute at least the first ML process to authenticate a new user responsive to completing training of the one or more first classification neural networks.
9. The system of claim 1 , wherein the one or more first classification neural networks comprise a deep neural network (“DNN”), wherein the DNN is configured to:
generate an array of values in response to the input of the at least one unclassified encrypted feature vector during authentication; and
determine a label or unknown result based on analyzing the generated array of values.
10. The system of claim 1 , wherein the generation neural networks comprise at least one learning network configured to accept plain text biometric as input and generate distance measurable encrypted feature vectors as output.
11. The system of claim 1 , wherein the one or more first classification neural networks are configured to return a label for identification or an unknown result, responsive to input of encrypted feature vector input.
12. The system of claim 1 , wherein the at least one processor is configured to:
determine a probability of match using the one or more first classification neural networks is below a threshold value; and
validate an unknown result output by the one or more first classification neural networks based on distance analysis of a highest probability match compared to the input feature vectors.
13. A computer implemented method for privacy enabled authentication, the method comprising:
executing, by at least one processor, a selection from a first machine learning (“ML”) process and a second ML process responsive to an authentication mode;
wherein executing the first ML process includes:
classifying distance measurable encrypted feature vector inputs as part of authentication using a first classification neural network once trained;
wherein executing the second ML process includes:
accepting plain text biometric inputs with a generation neural network to generate distance measurable encrypted feature vectors as an output of the generation neural network;
comparing distances between distance measurable encrypted feature vectors during identification or authentication; and
validating, by the at least one processor, that identification results produced by the selected first and second ML processes are based on a live submission from a live user, wherein validating includes determining liveness in multiple dimensions including at least a liveness evaluation of identification or authentication inputs are of a type matching a type submitted to the selected first and second ML process, as part of the evaluation of the multiple dimensions.
14. The method of claim 13 , wherein executing the first ML process includes accepting distance measurable encrypted feature vector and label inputs during training of one or more first classification neural networks, and defining the plurality of identification classes.
15. The method of claim 13 , further comprising:
determining one or more distances between encrypted feature vectors produced by the generation neural network;
excluding encrypted feature vectors having one or more distances exceeding a threshold distance for subsequent training processes; and
including encrypted feature vectors having distances within the threshold distance for subsequent training processes.
16. The method of claim 13 , further comprising determining the authentication mode that includes an enrollment mode for establishing a new entity for subsequent identification or authentication.
17. The method of claim 16 , further comprising triggering at least the second ML process responsive to determining a current authentication mode includes the enrollment mode.
18. The method of claim 17 , further comprising triggering at least training operations of the first or second ML processes responsive to determining that the current authentication mode includes the enrollment mode.
19. The method of claim 18 , further comprising executing at least the second ML process to authenticate the new user until at least a period of time required for training the one or more first classification neural networks expires.
20. The method of claim 18 , further comprising executing at least the first ML process to authenticate a new user responsive to completing training of the one or more first classification neural networks.