System and method for performing identity authentication based on de-identified data

1. A method of performing identity authentication based on de-identified data, the method comprising:

receiving, by a processor, a data item from a user;

creating, by the processor, a de-identified data item by applying a de-identification function r on the data item,

training, by the processor, a transformation function p and a key generation function with a loss function of d 1 (f(r(x i ), (p(x j , k x i )), f(x i , x j )), where (x i , x j ) are a pair of training data items, d 1 , is a machine learning function, and f is a recognition function;

generating, by the processor, using the key generation function, an authentication key, based on the received data item and the de-identified data item;

receiving a new data item for authentication;

generating, by the processor, a new de-identified data item by applying the transformation function on the new data item and the authentication key; and

comparing, by the processor, the new de-identified data item with the de-identified data item to authenticate the identity of the user.

2. The method of claim 1 , further comprising storing the authentication key in the database.

3. The method of claim 1 , wherein the new data item is received form a user's computerized device.

4. The method of claim 1 , further comprising training a computerized neural network to generate authentication keys capable of modifying a received data item into a de-identified data item that corresponds to a de-identified data item of the same user.

5. The method of claim 4 , wherein the computerized neural network is trained on a data set of pairs of original data and de-identified data.

6. The method of claim 4 , further comprising creating a key generation algorithm configured to generate one-way authentication keys for future authentication of de-identified data, wherein the key generation algorithm is created by the computerized neural network.

7. The method of claim 1 , further comprising executing a de-identification algorithm that performs at least one of perturbation and permutation on received data items with a corresponding authentication key.

8. The method of claim 7 , further comprising applying, by the processor, a recognition function on the received data items to return a probability of the data items belonging to the same identity.

9. The method of claim 1 , further comprising re-generating the authentication key.

10. The method of claim 1 , wherein the data item is an image of a face of a user.

11. A data authentication system comprising:

a computerized device, comprising data items for authentication;

a database, comprising de-identified data, and

a processor, coupled to the computerized device and to the database, wherein the processor is configured to:

receive a data item from a user;

create a de-identified data item by applying a de-identification function r on the data item,

training, by the processor, a transformation function p and a key generation function with a loss function of d 1 (f(r(x i ), (p(x j , k x i )), f(x i , x j )), where (x i , x j ) are a pair of training data items, d 1 , is a machine learning function, and f is a recognition function;

generating, by the processor, using the key generation function, an authentication key, based on the received data item and the de-identified data item;

receive a new data item for authentication;

generate a new de-identified data item by applying the transformation function on the new data item and the authentication key; and

compare the new de-identified data item with the de-identified data item to authenticate the identity of the user.

12. The system of claim 11 , further comprising at least one computerized neural network, coupled to the processor, and configured to analyze the de-identified data from the database.

13. The system of claim 11 , wherein the authentication key has a predefined length corresponding to the data item it was generated for.

14. The system of claim 11 , further comprising a detector, to detect at least one data item.

15. The system of claim 11 , further comprising:

an enrollment module to create the de-identified data item; and

an authentication module to authenticate identity of new data items.

16. The system of claim 15 , wherein the enrollment module comprises an authentication key generator and a de-identification function, configured to store at least one de-identified data item at the database.

17. The system of claim 15 , wherein the authentication module receives the de-identified data item and corresponding authentication key from the database to carry out authentication of a newly received data item.

18. The system of claim 11 , wherein the authentication key is re-generated.