Multifactor handwritten signature verification

1. A system, comprising:

a memory; and

a processor communicatively coupled to the memory, wherein the processor is configured to:

generate a signature model based on a set of timestamped reference signatures associated with a user;

receive a signature;

determine, based on the signature model and a timestamp of the signature, that the signature is valid; and

in response to the determining that the signature is valid, authenticate the signature, wherein the authenticating comprises:

generating a signature progression score indicating degrees of change in the signature relative to the set of reference signatures;

generating a secondary progression score indicating degrees of change in current secondary identifying information relative to a set of reference secondary identifying information; and

determining whether the signature progression score is consistent with the secondary progression score.

2. The system of claim 1 , wherein the processor is further configured to update the signature model to include the signature, the timestamp, and results of the determining that the signature is valid.

3. The system of claim 1 , wherein the signature model is a progression model.

4. A method, comprising:

generating a signature model based on a set of timestamped reference signatures associated with a user;

receiving a signature;

determining, based on the signature model and a timestamp of the signature, that the signature is valid; and

in response to the determining that the signature is valid, authenticating the signature, wherein the authenticating comprises:

generating a signature progression score indicating degrees of change in the signature relative to the set of reference signatures;

generating a secondary progression score indicating degrees of change in current secondary identifying information relative to a set of reference secondary identifying information; and

determining whether the signature progression score is consistent with the secondary progression score.

5. The method of claim 4 , further comprising updating the signature model to include the signature, the timestamp, and results of the determining that the signature is valid.

6. The method of claim 4 , wherein the signature model is a progression model.

7. The method of claim 6 , wherein the signature is determined to be valid when the signature is consistent with a sequence of the reference signatures over time.

8. The method of claim 4 , wherein the signature model is a generative model.

9. The method of claim 8 , wherein the signature is determined to be valid if the signature matches a predicted signature generated by the signature model for the timestamp.

10. The method of claim 4 , wherein the reference secondary identifying information comprises timestamped biometric data.

11. The method of claim 4 , wherein the signature model is based on variation over time in handwriting of the user.

12. The method of claim 4 , wherein the reference secondary identifying information is related to factors affecting handwriting of the user.

13. The method of claim 12 , wherein the factors comprise age and health of the user.

14. The method of claim 4 , wherein the signature progression score predicts an amount of time elapsed between the signature and the reference signatures.

15. The method of claim 14 , wherein the signature progression score is weighted based on a confidence value for the predicted amount of time.

16. The method of claim 4 , wherein the signature progression score predicts an amount of time elapsed between the signature and the reference signatures, and wherein the signature progression score is weighted based on a confidence value for the predicted amount of time elapsed between the signature and the reference signatures.

17. The method of claim 16 , wherein the secondary progression score predicts an amount of time elapsed between the current secondary identifying information and the reference secondary identifying information, and wherein the secondary progression score is weighted based on a confidence value for the predicted amount of time elapsed between the current secondary identifying information and the reference secondary identifying information.

18. The method of claim 17 , wherein the determining whether the signature progression score is consistent with the secondary progression score comprises comparing the weighted secondary progression score with the weighted signature progression score.

19. The method of claim 4 , wherein access to a reference storage containing the reference signatures and the reference secondary information is provided in response to the determining that the signature is valid.

20. The method of claim 19 , wherein the reference storage is a blockchain database.

21. A computer program product, comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause a device to perform a method, the method comprising:

generating a signature model based on a set of timestamped reference signatures associated with a user;

receiving a signature;

determining, based on the signature model and a timestamp of the signature, that the signature is valid; and

in response to the determining that the signature is valid, authenticating the signature, wherein the authenticating comprises:

generating a signature progression score indicating degrees of change in the signature relative to the set of reference signatures;

generating a secondary progression score indicating degrees of change in current secondary identifying information relative to a set of reference secondary identifying information; and

determining whether the signature progression score is consistent with the secondary progression score.