Methods and arrangements to log implementation of controls to mitigate risk

Patent metadata

Field	Value
Publication number	US-2024242151-A1
Application number	US-202318155944-A
Country	US
Kind code	A1
Filing date	Jan 18, 2023
Priority date	Jan 18, 2023
Publication date	Jul 18, 2024
Grant date	—

Abstract

Logic may identify information of a first electronic mail document associated with a control, the control to comprise a process to mitigate a risk. Logic may select the electronic mail document based on the information. Logic may determine metadata for the electronic mail document, the metadata. Logic may generate a first value representative of the electronic mail document based on application of a mathematical algorithm. Logic may generate a log entry for the electronic mail document comprising the metadata and the first value. Logic may encrypt the log entry with an encryption key. And logic may store the log entry in an encrypted ledger with a log entry date and a unique log entry identifier.

First claim

What is claimed is:

1 . An apparatus comprising:
memory; and logic circuitry coupled with the memory to perform operations to:
identify information of a first electronic mail document associated with a control, the control to comprise a process to mitigate a risk;
select the first electronic mail document based on the information;
determine metadata for the electronic mail document, the metadata comprising an email identifier, an email address, and an email date;
generate a first value representative of the electronic mail document based on application of a mathematical algorithm;
generate a log entry for the electronic mail document comprising the metadata and the first value;
encrypt the log entry with an encryption key; and
store the log entry in an encrypted ledger with a log entry date and a unique log entry identifier.

2 . The apparatus of claim 1 , the logic circuitry to further perform operations to:
monitor for additional electronic mail documents in an email thread associated with the first electronic mail document; and store, in the encrypted ledger, a log entry for each of the additional electronic mail documents in an email thread associated with the first electronic mail document.

3 . The apparatus of claim 2 , the logic circuitry to further perform operations to:
monitor for attempts to modify the first electronic mail document and the additional electronic mail documents in an email thread associated with the first electronic mail document; and block the attempts to modify the first electronic mail document and the additional electronic mail documents in an email thread associated with the first electronic mail document.

4 . The apparatus of claim 1 , the operation to select the electronic mail document to include operations to:
identify one or more tags associated with the control, and correlate the one or more tags with the information.

5 . The apparatus of claim 1 , the operation to select the electronic mail document to include operations to:
identify one or more tags associated with the control, and correlate the one or more tags with the information associated with an attachment of in the first electronic mail document.

6 . The apparatus of claim 1 , the operation to identify information to include operations to:
generate input data for an inference engine based on the first electronic mail document, provide the input data to the input of the inference engine, and determine that the first electronic mail document is associated with the control based on an output of the inference engine.

7 . The apparatus of claim 6 , wherein the inference engine comprises a machine learning engine trained with training data including electronic mail documents associated with one or more controls in a set of controls, the one or more controls to include the control.

8 . The apparatus of claim 1 , wherein the metadata comprises a from email address, a to email address, a cc email address, a subject line, and one or more control identifiers.

9 . The apparatus of claim 1 , wherein the metadata comprises information from attachments of the first electronic mail document.

10 . The apparatus of claim 1 , wherein the first value comprises a checksum of the electronic mail document, a hash of the electronic mail document, or a combination thereof.

11 . A non-transitory storage medium containing instructions, which when executed by a processor, cause the processor to perform operations, the operations to:
parse metadata of one or more electronic mail documents; infer information of a first electronic mail document associated with a set of controls; access the set of controls to obtain data associated with the set of controls; correlate the information with the set of controls based on the data associated with the set of controls; select the first electronic mail document based on correlation of the information; generate a log entry for the electronic mail document comprising metadata and a first value, the first value comprising an encoded representation of the electronic mail document; and store the log entry in an encrypted ledger with a log entry date and a unique log entry identifier.

12 . The non-transitory storage medium of claim 11 , wherein the operations further comprise operations to:
monitor for additional electronic mail documents in an email thread associated with the first electronic mail document; and store, in the encrypted ledger, a log entry for each of the additional electronic mail documents in an email thread associated with the first electronic mail document.

13 . The non-transitory storage medium of claim 12 , wherein the operations further comprise operations to:
monitor for attempts to modify the first electronic mail document and the additional electronic mail documents in an email thread associated with the first electronic mail document; and block the attempts to modify the first electronic mail document and the additional electronic mail documents in an email thread associated with the first electronic mail document.

14 . The non-transitory storage medium of claim 11 , wherein the operation to parse metadata includes operations to:
generate input data based on the metadata of the first electronic mail document and attachments, and provide the input data to a natural language processor, the natural language processor to determine tags associated with the first electronic mail document.

15 . The non-transitory storage medium of claim 14 , wherein the operation to infer information includes operations to correlate the one or more tags with the one or more controls via a machine learning engine to classify the electronic mail document as related to the set of controls or to determine a probability that the electronic mail document is related to the one or more controls.

16 . The non-transitory storage medium of claim 11 , wherein the operation to infer information includes operations to:
generate input data for an inference engine based on the first electronic mail document, provide the input data to the input of the inference engine, and determine that the first electronic mail document is associated with the control based on an output of the inference engine.

17 . The non-transitory storage medium of claim 16 , wherein the inference engine comprises a machine learning engine trained with training data including electronic mail documents associated with one or more controls in a set of controls, the one or more controls to include the control.

18 . The non-transitory storage medium of claim 11 , wherein the metadata comprises a from email address, a to email address, a cc email address, a subject line, and one or more control identifiers.

19 . The non-transitory storage medium of claim 11 , wherein the first value comprises a checksum of the electronic mail document, a hash of the electronic mail document, or a combination thereof.

20 . An apparatus, the apparatus comprising:
memory; and logic circuitry coupled with the memory to:
access training data based on historical electronic mail documents to train a machine learning engine to infer an association between electronic mail documents and the one or more controls;
infer associations between the historical electronic mail documents in a testing portion of the training data and the one or more controls;
compare the associations inferred against known associations between the historical electronic mail documents and the one or more controls in the

Assignees

• Capital One Services Llc

Inventors

• Cheng Lin Ni Lisa
• Parker Ryan M
• Petrunin Sergey
• Williams Gary B
• Coble Piper Alexandra

Classifications

• G06F21/64

  Protecting data integrity, e.g. using checksums, certificates or signatures · CPC title

• H04L9/3236

  using cryptographic hash functions · CPC title

• H04L51/212

  using filtering or selective blocking · CPC title

• G06Q10/107

  Computer-aided management of electronic mailing [e-mailing] · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title