Methods, systems, and media for secure authentication of users based on a biometric identifier and knowledge-based secondary information

1. A method for authenticating users in a biometric recognition system, the method comprising:

receiving an indication that a biometric identifier is to be used to authenticate a user to a service;

receiving (i) the biometric identifier of the user from a capture device and (ii) knowledge-based secondary information associated with the user from an input device;

generating a set of random points based on a random seed, wherein the random seed is associated with the service;

determining a feature vector that corresponds to the biometric identifier;

generating a map of the feature vector to the set of random points;

calculating a hash based on the map of the feature vector and the knowledge-based secondary information;

transmitting the hash to a server device for verification;

in response to transmitting the hash to the server device, receiving a response indicating whether the hash matches a previously stored hash that was stored in the server device; and

determining whether to automatically authenticate the user to the service based on the response from the server device.

2. The method of claim 1 , wherein the biometric identifier is a facial image that is received using an image capturing device.

3. The method of claim 2 , further comprising:

calculating a group of Voronoi cells based on the set of random points; and

determining a mapping of the feature vector of the facial image to the group of Voronoi cells.

4. The method of claim 3 , wherein the group of Voronoi cells is calculated by identifying, for each random point in the set of random points, a region in which points in the region are close to the random point based on a distance metric.

5. The method of claim 3 , wherein the hash is calculated based on the mapping of the feature vector to the group of Voronoi cells.

6. The method of claim 1 , wherein a plurality of feature vectors are determined to correspond to the biometric identifier and wherein the hash is calculated for each of the plurality of feature vectors with the knowledge-based secondary information associated with the user.

7. A system for authenticating users in a biometric recognition system, the system comprising:

a memory; and

a hardware processor that, when configured to execute computer executable instructions stored in the memory, is configured to:

receive an indication that a biometric identifier is to be used to authenticate a user to a service;

receive (i) the biometric identifier of the user from a capture device and (ii) knowledge-based secondary information associated with the user from an input device;

generate a set of random points based on a random seed, wherein the random seed is based on the identifier of the device;

determine a feature vector that corresponds to the biometric identifier;

generate a map of the feature vector to the set of random points;

calculate a hash based on the map of the feature vector and the knowledge-based secondary information;

transmit the hash to a server device for verification;

in response to transmitting the hash to the server device, receive a response indicating whether the hash matches a previously stored hash that was stored in the server device; and

determine whether to automatically authenticate the user to the service based on the response from the server device.

8. The system of claim 7 , wherein the biometric identifier is a facial image that is received using an image capturing device.

9. The system of claim 8 , wherein the hardware processor is further configured to:

generate a set of random points based on a random seed;

calculate a group of Voronoi cells based on the set of random points; and

determine a mapping of the feature vector of the facial image to the group of Voronoi cells.

10. The system of claim 9 , wherein the group of Voronoi cells is calculated by identifying, for each random point in the set of random points, a region in which points in the region are close to the random point based on a distance metric.

11. The system of claim 9 , wherein the hash is calculated based on the mapping of the feature vector to the group of Voronoi cells.

12. The system of claim 7 , wherein a plurality of Voronoi cell identifiers are determined to correspond to the biometric identifier and wherein the hash is calculated for each of the plurality of Voronoi cell identifiers with the knowledge-based secondary information associated with the user.

13. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for authenticating users in a biometric recognition system, the method comprising:

receiving an indication that a biometric identifier is to be used to authenticate a user to a service;

receiving (i) the biometric identifier of the user from a capture device and (ii) knowledge-based secondary information associated with the user from an input device;

generate a set of random points based on a random seed, wherein the random seed is based on the identifier of the device;

determining a feature vector that corresponds to the biometric identifier;

generate a map of the feature vector to the set of random points;

calculating a hash based on the map of the feature vector and the knowledge-based secondary information;

transmitting the hash to a server device for verification;

in response to transmitting the hash to the server device, receiving a response indicating whether the hash matches a previously stored hash that was stored in the server device; and

determining whether to automatically authenticate the user to the service based on the response from the server device.

14. The non-transitory computer-readable medium of claim 13 , wherein the biometric identifier is a facial image that is received using an image capturing device.

15. The non-transitory computer-readable medium of claim 14 , wherein the method further comprises:

calculating a group of Voronoi cells based on the set of random points; and

determining a mapping of the feature vector of the facial image to the group of Voronoi cells.

16. The non-transitory computer-readable medium of claim 14 , wherein the group of Voronoi cells is calculated by identifying, for each random point in the set of random points, a region in which points in the region are close to the random point based on a distance metric.

17. The non-transitory computer-readable medium of claim 14 , wherein the hash is calculated based on the mapping of the feature vector to the group of Voronoi cells.