Digital Health Passport to Verify Identity of a User

Abstract

The technology disclosed relates to authenticating users using a plurality of non-deterministic biometric identifiers. The method includes generating a scannable code upon receiving a success nonce from a registration server. The registration server can access a user identifier and a hash of at least a signature using the success nonce. The signature can be generated based at least in part upon a biometric identifier of a user. The method includes recreating the hash of the signature stored by the registration server. The method includes generating the scannable code by encrypting the success nonce and the recreated hash. The biometric identifier of the user is generated by feeding a plurality of non-deterministic biometric inputs to a trained machine learning model producing a plurality of feature vectors. The method includes projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user.

1 . A computer-implemented method of generating a scannable code, the method including:
 receiving, from a registration server, a success nonce, usable by the registration server to access a user identifier and access a hash of at least a signature, generated based at least in part upon a biometric identifier for a user;   recreating the hash of the at least the signature stored by the registration server; and   generating the scannable code including encrypting the success nonce and the recreated hash and producing the scannable code from results of the encrypting;
 wherein the biometric identifier of the user was generated by feeding a plurality of non-deterministic biometric inputs, including a plurality of facial images and a plurality of voice samples of a user, to a trained machine learning model producing a plurality of feature vectors, projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user based on the feature vectors as projected. 
   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the user identifier comprises a facial image of the user. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the user identifier comprises a voice sample of the user. 
     
     
         4 . The computer-implemented method of  claim 1 , further including:
 receiving a shared encryption key and a public encryption key.   
     
     
         5 . The computer-implemented method of  claim 4 , further including:
 sending to the registration server, for validating, a signature for a unique identifier for the user wherein the signature for the unique identifier for the user is generated by applying the shared encryption key to the unique identifier for the user.   
     
     
         6 . The computer-implemented method of  claim 5 , further including:
 generating the hash of at least the signature and the shared key.   
     
     
         7 . The computer-implemented method of  claim 1 , recreating the hash further including:
 using a shared key stored by the registration server.   
     
     
         8 . The computer-implemented method of  claim 1 , wherein the success nonce is a one-time use code for use with the scannable code. 
     
     
         9 . A computer-implemented method of verifying a return-to-work request from a user by a registration server, the method including:
 extracting a nonce code and a recreated hash from a scannable code received from a validator that has scanned the scannable code wherein the scannable code encodes the nonce code, previously generated by the registration server, and the recreated hash, previously associated by the registration server with the nonce code;   using the nonce code to access a hash of record and an identifier of the user;   sending the validator, the identifier of the user and a success message to return-to-work;
 wherein the nonce code was previously generated by feeding a plurality of non-deterministic biometric inputs, including a plurality of facial images and a plurality of voice samples of the user, to a trained machine learning model producing a plurality of feature vectors, projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user based on the feature vectors as projected. 
   
     
     
         10 . The computer-implemented method of  claim 9 , further including:
 encrypting the identifier of the user and the success message with a public encryption key of the registration server.   
     
     
         11 . The computer-implemented method of  claim 9 , wherein the identifier of the user comprises a facial image the user. 
     
     
         12 . The computer-implemented method of  claim 9 , wherein the identifier of the user comprises a voice sample of the user. 
     
     
         13 . A system including one or more processors coupled to memory, the memory loaded with computer instructions to generate a scannable code, the instructions, when executed on the processors, implement actions comprising:
 receiving, from a registration server, a success nonce, usable by the registration server to access a user identifier and access a hash of at least a signature, generated based at least in part upon a biometric identifier;   recreating the hash of the at least the signature stored by the registration server; and   generating the scannable code including encrypting the success nonce and the recreated hash and producing the scannable code from results of the encrypting;
 wherein the biometric identifier of a user was generated by feeding a plurality of non-deterministic biometric inputs, including a plurality of facial images and a plurality of voice samples of a user, to a trained machine learning model producing a plurality of feature vectors, projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user based on the feature vectors as projected. 
   
     
     
         14 . The system of  claim 13 , wherein the user identifier comprises a facial image of the user. 
     
     
         15 . The system of  claim 13 , wherein the user identifier comprises a voice sample of the user. 
     
     
         16 . The system of  claim 13 , further implementing actions comprising:
 receiving a shared encryption key and a public encryption key.   
     
     
         17 . The system of  claim 16 , further implementing actions comprising:
 sending to the registration server, for validating, a signature for a unique identifier for the user wherein the signature for the unique identifier for the user is generated by applying the shared encryption key to the unique identifier for the user.   
     
     
         18 . A non-transitory computer readable storage medium impressed with computer program instructions to generate a scannable code, the instructions, when executed on a processor, implement a method comprising:
 receiving, from a registration server, a success nonce, usable by the registration server to access a user identifier and access a hash of at least a signature, generated based at least in part upon a biometric identifier;   recreating the hash of the at least the signature stored by the registration server; and   generating the scannable code including encrypting the success nonce and the recreated hash and producing the scannable code from results of the encrypting;
 wherein the biometric identifier of a user was generated by feeding a plurality of non-deterministic biometric inputs, including a plurality of facial images and a plurality of voice samples of a user, to a trained machine learning model producing a plurality of feature vectors, projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user based on the feature vectors as projected. 
   
     
     
         19 . The non-transitory computer readable storage medium of  claim 18 , wherein the user identifier comprises a facial image of the user. 
     
     
         20 . The non-transitory computer readable storage medium of  claim 18 , wherein the user identifier comprises a voice sample of the user.