Systems and methods for private authentication with helper networks
Helper neural network can play a role in augmenting authentication services that are based on neural network architectures. For example, helper networks are configured to operate as a gateway on identification information used to identify users, enroll users, and/or construct authentication models (e.g., embedding and/or prediction networks). Assuming, that both good and bad identification information samples are taken as part of identification information capture, the helper networks operate to filter out bad identification information prior to training, which prevents, for example, identification information that is valid but poorly captured from impacting identification, training, and/or prediction using various neural networks. Additionally, helper networks can also identify and prevent presentation attacks or submission of spoofed identification information as part of processing and/or validation.
1. An authentication system for privacy-enabled authentication, the system comprising:
at least one processor operatively connected to a memory;
an authentication data gateway, executed by the at least one processor, configured to filter invalid identification information, the authentication data gateway comprising at least:
a first pre-trained geometry helper network, wherein the first pre-trained geometry helper network is trained on a plurality of identification samples of a first type to filter identifying characteristics from input identification information of the first type, and configured to:
process the input identification information of the first type,
accept as input plaintext identification information of the first type, and
output the processed input identification information of the first type, wherein the processed input identification information of the first type includes the filtered identifying characteristics from the input identification information of the first type; and
a first pre-trained validation helper network trained on a plurality of valid and invalid samples of the first type, the first pre-trained validation helper network associated with the first pre-trained geometry helper network, and configured to:
process the input identification information of the first type,
accept the output of the first pre-trained geometry helper neural network, and
validate the input identification information of the first type or reject the input identification information of the first type,
wherein the geometry and validation helper networks process the input identification information and output filtered identification information used for subsequent enrollment and identification functions; and
wherein the authentication data gateway further comprises a plurality of validation helper networks each associated with a respective type of identification information, wherein each of the plurality of validation helper networks generate at least a binary evaluation of respective identification inputs to establish validity.
2. The system of claim 1 , wherein the authentication data gateway is configured to filter bad authentication data from training data sets used to build embedding network models.
3. The system of claim 1 , wherein the first pre-trained validation helper network is trained on evaluation criteria independent of the subject seeking to be enrolled or authenticated.
4. The system of claim 1 , wherein the authentication data gateway further comprises at least a second geometry helper network and a second validation helper network pair configured to process and valid identification information of a second type.
5. The system of claim 1 , wherein the first pre-trained validation helper network is configured process an image input as identification information, and output a probability that the image input is invalid.
6. The system of claim 1 , wherein the first pre-trained validation helper network is configured to process an image input as identification information, and output a probability that the image input is a presentation attack.
7. The system of claim 1 , wherein the first pre-trained validation helper network is configured to:
process a video input as identification information; and
output a probability that the video input is invalid.
8. The system of claim 1 , wherein the first pre-trained validation helper network is configured to:
process a video input as identification information, and
output a probability that the video input is a presentation attack.
9. A computer implemented method for privacy-enabled authentication, the method comprising:
filtering, by at least one processor, invalid identification information;
executing by the at least one processor, a first pre-trained geometry helper network, wherein the first pre-trained geometry helper network is trained on a plurality of identification samples of a first type to filter identifying characteristics from input identification information of the first type;
accepting, by the first pre-trained geometry helper network, plaintext identification information of the first type as input;
generating processed input identification information of the first type;
executing by the at least one processor, a first pre-trained validation helper network, trained on a plurality of valid and invalid samples of the first type, the first pre-trained validation helper network;
accepting the output of the first pre-trained geometry helper neural network;
validating the input identification information of the first type or reject the identification information of the first type;
wherein the first pre-trained geometry and first pre-trained validation helper networks process the input identification information and output the filtered identification information used for subsequent enrollment and identification functions; and
wherein the method further comprises executing a plurality of validation helper networks each associated with a respective type of identification information, wherein each of the plurality of validation helper networks generate at least a binary evaluation of respective identification inputs to establish validity.
10. The method of claim 9 , wherein the method further comprises filtering bad authentication data from training data sets used to build embedding network models.
11. The method of claim 9 , wherein the method further comprises training the first pre-trained validation helper network on evaluation criteria independent of the subject seeking to be enrolled or authenticated.
12. The method of claim 9 , wherein the method further comprises executing at least a second geometry helper network and a second validation helper network pair configured to process and validate identification information of a second type.
13. The method of claim 9 , wherein the method further comprises processing, by the first pre-trained validation helper network an image input as identification information, and output a probability that the image input is invalid.
14. The method of claim 9 , wherein the method further comprises processing an image input as identification information, and generating a probability that the image input is a presentation attack, by the first pre-trained validation helper network.
15. The method of claim 9 , wherein the method further comprises
processing, the first pre-trained validation helper network, a video input as identification information; and
generating, the first pre-trained validation helper network, a probability that the video input is invalid, by the first pre-trained validation helper network.
16. The method of claim 9 , wherein the method further comprises
processing, the first pre-trained validation helper network, a video input as identification information, and
generating, the first pre-trained validation helper network, a probability that the video input is a presentation attack.