IP Library Granted Patent US 12683761
Granted Patent B2
US 12683761 · App. 18/886,357 · Granted Jul 14, 2026

Confidential automated speech recognition

Inventors: Cornelius Patrick Glackin (London, GB); Nigel Henry Cannings (London, GB)
Assignee: VERINT SYSTEMS UK LIMITED
H04L9/0631G06F21/57G06F21/6209G10L15/22H04L9/0825H04L9/3066
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12683761
App. No.
18/886,357
Filed
Sep 16, 2024
Granted
Jul 14, 2026
Kind
B2
Art Unit
2447
USPC
713/165
Abstract

The present invention provides a secure method for outsourcing data analysis to a third party without the third party being able to access the data in clear. In the present invention, the client's data is never written to disk, this feature provides the security. The data is decrypted and processed in the enclave which ensures that the data is secure and hidden at all times when it is visible “in clear”.

Claims (37)

1 . A computer implemented method for confidential data processing, the method comprising:

generating, by an enclave, an enclave public key;

transmitting, by the enclave, the enclave public key to an Application Programming Interface (API), wherein the enclave public key is stored in an encrypted memory of the enclave along with a corresponding enclave private key;

receiving, by the enclave from the API, one or more encrypted files and a client public key;

decrypting, by the enclave, the one or more encrypted files, using the enclave private key;

storing the decrypted one or more files in the encrypted memory of the enclave;

processing, by the enclave, the decrypted one or more files to produce one or more result files;

encrypting, by the enclave, the one or more result files using the client public key; and

sending, by the enclave, the one or more result files to the API for decryption by a downstream entity.

2 . The computer implemented method of claim 1 , wherein the enclave is a cloud enclave.

3 . The computer implemented method of claim 1 , wherein the enclave public key is ephemeral.

4 . The computer implemented method of claim 1 , wherein the enclave is one of a plurality of enclaves; and

the API selects one of the plurality of enclaves for requesting the enclave public key dependent on one or both of size of enclave memory, enclave processing speed.

5 . The computer implemented method of claim 1 , wherein the one or more files are audio files.

6 . The computer implemented method of claim 5 , wherein the processing carried out by the enclave is automatic speech recognition.

7 . The computer implemented method of claim 1 , wherein the API provides one or more data processing services.

8 . A data processing system comprising means for carrying out the method of claim 1 .

9 . A processor configured to transmit a computer program containing instructions for performing a method as claimed in claim 1 .

10 . The computer implemented method of claim 1 , wherein the downstream entity is a client computer.

11 . A system comprising:

at least one processor; and

at least one data storage comprising instructions which, when executed by the at least one processor, cause the at least one processor to perform a method for conducting a mobile device transaction, the method comprising:

generating, by an enclave, an enclave public key;

transmitting, by the enclave, the enclave public key to an Application Programming Interface (API), wherein the enclave public key is stored in an encrypted memory of the enclave along with a corresponding enclave private key;

receiving, by the enclave from the API, one or more encrypted files and a client public key;

decrypting, by the enclave, the one or more encrypted files, using the enclave private key;

storing the decrypted one or more files in the encrypted memory of the enclave;

processing, by the enclave, the decrypted one or more files to produce one or more result files;

encrypting, by the enclave, the one or more result files using the client public key; and

sending, by the enclave, the one or more result files to the API for decryption by a downstream entity.

12 . The system of claim 11 , wherein the enclave is a cloud enclave.

13 . The system of claim 11 , wherein the enclave public key is ephemeral.

14 . The system of claim 11 , wherein the enclave is one of a plurality of enclaves; and the API selects one of the plurality of enclaves for requesting the enclave public key dependent on one or both of size of enclave memory, enclave processing speed.

15 . The system of claim 11 , wherein the one or more files are audio files.

16 . The system of claim 15 , wherein the processing carried out by the enclave is automatic speech recognition.

17 . The system of claim 11 , wherein the API provides one or more data processing services.

18 . The system of claim 11 , wherein the downstream entity is a client computer.