Granted Patent B2

US 12,542,650 · App. 18/376,138 · Granted Feb 3, 2026

Inventors: Saurabh Garg (Faridabad, IN); Bhagat Allugubelly (Hyderabad, IN); Maneesh Sethia (Telangana, IN)

Assignee: Bank of America Corporation

H04L9/008G06F21/602

Abstract

Claims (58)

1 . A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

train, using smart contract and file type information, a homomorphic encryption model, wherein training the homomorphic encryption model configures the homomorphic encryption model, by establishing stored correlations between the file type information and the smart contracts, to identify, based on a given file type for a given input file, a corresponding smart contract defining a corresponding set of parameters, included in the given input file, for display, wherein the homomorphic encryption model comprises one of a supervised learning model or an unsupervised learning model, and wherein the homomorphic encryption model is further trained using historical system performance information, and wherein training the homomorphic encryption model using the historical system performance information configures the homomorphic encryption model to output, for the given input file, one or more corresponding processing resources of the computing platform at which to perform homomorphic encryption of an encrypted file;

receive an unencrypted file;

identify, by inputting the unencrypted file into the homomorphic encryption model, a smart contract defining one or more parameters for display, wherein the homomorphic encryption model identifies the smart contract by:

comparing a file type of the unencrypted file to the file type information used to train the homomorphic encryption model, and

identifying, based on the stored correlations between the file type information and the smart contracts, the smart contract corresponding to the file type;

encrypt, using homomorphic encryption, the unencrypted file to produce the encrypted file;

store the encrypted file;

receive, via an application programming interface (API) at a user device, a request to access the encrypted file and authentication credentials; and

send, based on the smart contract, based on validation of the authentication credentials, and for display at the user device via the API, the parameters for display.

2 . The computing platform of claim 1 , wherein the homomorphic encryption model comprises an artificial intelligence (AI) model.

3 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

identify, by inputting the unencrypted file and current system performance information into the homomorphic encryption model, one or more processing resources of the computing platform at which to perform the homomorphic encryption of the encrypted file.

4 . The computing platform of claim 3 , wherein the current system performance information comprises system latency, available memory, available processing resources, and system load.

5 . The computing platform of claim 1 , wherein the smart contract defines the one or more parameters for display and one or more parameters to remain concealed.

6 . The computing platform of claim 1 , wherein the smart contract defines different parameters for display for different users.

7 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

generate a file token representing the unencrypted file; and

store, using a distributed ledger, the file token.

8 . The computing platform of claim 7 , wherein the file token comprises one of a non-fungible token (NFT) or a crypto token.

9 . The computing platform of claim 1 , wherein sending the parameters for display comprises sending the parameters without decrypting the encrypted file.

10 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

update, based on the identified smart contract, the homomorphic encryption model.

11 . The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

identify, based on the authentication credentials, a user identity, wherein sending the parameters for display comprises sending, based on the user identity, a subset of the parameters for display.

12 . A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

training, using smart contract and file type information, a homomorphic encryption model, by establishing stored correlations between the file type information and the smart contracts, wherein training the homomorphic encryption model configures the homomorphic encryption model to identify, based on a given file type for a given input file, a corresponding smart contract defining a corresponding set of parameters, included in the given input file, for display, wherein the homomorphic encryption model comprises one of a supervised learning model or an unsupervised learning model, and wherein the homomorphic encryption model is further trained using historical system performance information, and wherein training the homomorphic encryption model using the historical system performance information configures the homomorphic encryption model to output, for the given input file, one or more corresponding processing resources of the computing platform at which to perform homomorphic encryption of an encrypted file;

receiving an unencrypted file;

identifying, by inputting the unencrypted file into the homomorphic encryption model, a smart contract defining one or more parameters for display, wherein the homomorphic encryption model identifies the smart contract by:

comparing a file type of the unencrypted file to the file type information used to train the homomorphic encryption model, and

identifying, based on the stored correlations between the file type information and the smart contracts, the smart contract corresponding to the file type;

encrypting, using homomorphic encryption, the unencrypted file to produce the encrypted file;

storing the encrypted file;

receiving, via an application programming interface (API) at a user device, a request to access the encrypted file; and

sending, based on the smart contract and for display at the user device via the API, the parameters for display.

13 . The method of claim 12 , wherein the homomorphic encryption model comprises an artificial intelligence (AI) model.

14 . The method of claim 12 , further comprising:

identifying, by inputting the unencrypted file and current system performance information into the homomorphic encryption model, one or more processing resources of the computing platform at which to perform the homomorphic encryption of the encrypted file.

15 . The method of claim 14 , wherein the current system performance information comprises system latency, available memory, available processing resources, and system load.

16 . The method of claim 12 , wherein the smart contract defines the one or more parameters for display and one or more parameters to remain concealed.

17 . The method of claim 12 , wherein the smart contract defines different parameters for display for different users.

18 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

train, using smart contract and file type information, a homomorphic encryption model, wherein training the homomorphic encryption model configures the homomorphic encryption model, by establishing stored correlations between the file type information and the smart contracts, to identify, based on a given file type for a given input file, a corresponding smart contract defining a corresponding set of parameters, included in the given input file, for display, wherein the homomorphic encryption model comprises one of a supervised learning model or an unsupervised learning model, and wherein the homomorphic encryption model is further trained using historical system performance information, and wherein training the homomorphic encryption model using the historical system performance information configures the homomorphic encryption model to output, for the given input file, one or more corresponding processing resources of the computing platform at which to perform homomorphic encryption of an encrypted file;

receive an unencrypted file;

identify, by inputting the unencrypted file into the homomorphic encryption model, a smart contract defining one or more parameters for display, wherein the homomorphic encryption model identifies the smart contract by:

comparing a file type of the unencrypted file to the file type information used to train the homomorphic encryption model, and

identifying, based on the stored correlations between the file type information and the smart contracts, the smart contract corresponding to the file type;

encrypt, using homomorphic encryption, the unencrypted file to produce the encrypted file;

store the encrypted file;

receive, via an application programming interface (API) at a user device, a request to access the encrypted file; and

send, based on the smart contract and for display at the user device via the API, the parameters for display.

19 . The one or more non-transitory computer-readable media of claim 18 , wherein the homomorphic encryption model comprises an artificial intelligence (AI) model.

20 . The one or more non-transitory computer-readable media of claim 18 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

identify, by inputting the unencrypted file and current system performance information into the homomorphic encryption model, one or more processing resources of the computing platform at which to perform the homomorphic encryption of the encrypted file.

Assignments (1)

Continuity (1)

References Cited (51)