# US 2020/0351310 A1 · Adaptive distributive data protection system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0351310 A1
- Document ID: US20200351310A1
- Status: Published application
- Kind: A1
- Application number: 16/402,495
- Filed: 2019-05-03
- Published: 2020-11-05
- Earliest claimed: 2019-05-03
- Assignees: Virtustream IP Holding Company LLC
- Applicants: Virtustream IP Holding Company LLC
- Inventors: Gregsie Leighton; Julius Bernotas; Vaidotas Simaitis
- Web page: https://patentgrep.com/patent/US20200351310A1

## CPC

- H04L 9/3239: {involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD}
- G06F 18/2148: {characterised by the process organisation or structure, e.g. boosting cascade}
- G06F 21/6227: {where protection concerns the structure of data, e.g. records, types, queries}
- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F 21/645: {using a third party}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- H04L 9/0637: {Modes of operation, e.g. cipher block chaining [CBC], electronic codebook [ECB] or Galois/counter mode [GCM]}
- H04L 9/3234: {involving additional secure or trusted devices, e.g. TPM, smartcard, USB or software token (network architectures or network communication protocols for supporting authentication of entities using an additional device in a packet data network H04L63/0853)}
- H04L 63/0428: {wherein the data content is protected, e.g. by encrypting or encapsulating the payload}
- H04L 63/205: {involving negotiation or determination of the one or more network security mechanisms to be used, e.g. by negotiation between the client and the server or between peers or by selection according to the capabilities of the entities involved (negotiation of communication capabilities H04L69/24)}
- H04L 9/50: {using hash chains, e.g. blockchains or hash trees}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments for protecting data stored and transmitted in a computer network, by receiving confidential data from a client, the data organized into labeled fields and corresponding data elements; filtering the received data to identify fields that require data masking; generating a security prediction on the corresponding data elements using a machine learning process; separating the masked data into tokenized data having a respective token associated with each corresponding data element; and storing the tokenized data on a blockchain secure ledger to ensure integrity of the received data and prevent an ability to tamper with the received data.

## Claims

### Claim 1

A method of protecting data stored and transmitted in a computer network, comprising:
receiving confidential data from a client, the data organized into labeled fields and corresponding data elements;
filtering the received data to identify fields that require data masking;
generating a security prediction on the corresponding data elements using a machine learning process;
separating the masked data into tokenized data having a respective token associated with each corresponding data element; and
storing the tokenized data on a blockchain secure ledger to ensure integrity of the received data and prevent an ability to tamper with the received data.

### Claim 2 (depends on 1)

The method of claim 1 wherein the network comprises a multi-tenant network, and wherein the tokenized data is split and separated on the basis of individual tenant ownership among multiple tenants.

### Claim 3 (depends on 2)

The method of claim 2 wherein the network comprises an enterprise scale network having storage devices storing the data in geographically distributed locations.

### Claim 4 (depends on 1)

The method of claim 1 wherein the machine learning process comprises at least one of a logistic regression algorithm and a decision tree algorithm.

### Claim 5 (depends on 4)

The method of claim 4 wherein the decision tree algorithm comprises one of a random forest algorithm and a boosting tree algorithm.

### Claim 6 (depends on 4)

The method of claim 4 wherein the machine learning process further categorizes data rules by data type, data usage, system context, confidentiality level, and minimum required encryption strength.

### Claim 7 (depends on 6)

The method of claim 6 wherein the machine learning process further categorizes law for protection by at least one of: data type, rationale, data type patterns, and confidentiality range.

### Claim 8 (depends on 6)

The method of claim 6 wherein an encryption method sets an encryption method, encryption strength, and encryption API (application programming interface) location and type.

### Claim 9 (depends on 1)

The method of claim 1 further comprising:
creating, in a server computer receiving the confidential data, a first sequence ID and second sequence ID from a User ID for the user, both based on a mask sequence of the received data;
sending the first sequence ID to the user; and
storing the second sequence ID with the User ID to facilitate reassembly of the data upon request by the user.

### Claim 10 (depends on 9)

The method of claim 9 further comprising:
receiving the request from the user to access the stored data, the request including the User ID;
finding the second sequence ID based on the received User ID;
combining the first sequence ID and second sequence ID to obtain the mask sequence;
retrieving the data from the storage using the obtained mask sequence; and
sending the data to the user.

### Claim 11

An apparatus protecting data stored and transmitted in a computer network, comprising:
an interface receiving confidential data from a client, the data organized into labeled fields and corresponding data elements;
a data encryption processor filtering the received data to identify fields that require data masking;
a machine learning data identification processor generating a security prediction on the corresponding data elements using a machine learning process;
a data tokenization processor separating the masked data into tokenized data having a respective token associated with each corresponding data element; and
a blockchain secure ledger data storage processor storing the tokenized data on a blockchain secure ledger to ensure integrity of the received data and prevent an ability to tamper with the received data.

### Claim 12 (depends on 11)

The apparatus of claim 11 wherein the network comprises a multi-tenant network, and wherein the tokenized data is split and separated on the basis of individual tenant ownership among multiple tenants, and wherein the network comprises an enterprise scale network having storage devices storing the data in geographically distributed locations.

### Claim 13 (depends on 11)

The apparatus of claim 11 wherein the machine learning process comprises at least one of a logistic regression algorithm and a decision tree algorithm, the decision tree algorithm comprising one of a random forest algorithm and a boosting tree algorithm.

### Claim 14 (depends on 11)

The apparatus of claim 11 wherein the machine learning process further categorizes data rules by data type, data usage, system context, confidentiality level, and minimum required encryption strength.

### Claim 15 (depends on 14)

The apparatus of claim 14 wherein the machine learning process further categorizes law for protection by at least one of: data type, rationale, data type patterns, and confidentiality range.

### Claim 16 (depends on 15)

The apparatus of claim 15 wherein an encryption method sets an encryption method, encryption strength, and encryption API (application programming interface) location and type.

### Claim 17 (depends on 11)

The apparatus of claim 11 wherein a first processing component further:
creates, in a server computer receiving the confidential data, a first sequence ID and second sequence ID from a User ID for the user, both based on a mask sequence of the received data;
sends the first sequence ID to the user; and
stores the second sequence ID with the User ID to facilitate reassembly of the data upon request by the user.

### Claim 18 (depends on 17)

The apparatus of claim 17 wherein a second processing component further:
receives the request from the user to access the stored data, the request including the User ID;
finds the second sequence ID based on the received User ID;
combines the first sequence ID and second sequence ID to obtain the mask sequence;
retrieves the data from the storage using the obtained mask sequence; and
sends the data to the user.

### Claim 19

A computer program product, comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein, the computer-readable program code adapted to be executed by one or more processors to perform a method of protecting data stored and transmitted in a computer network, by:
receiving confidential data from a client, the data organized into labeled fields and corresponding data elements;
filtering the received data to identify fields that require data masking;
generating a security prediction on the corresponding data elements using a machine learning process;
separating the masked data into tokenized data having a respective token associated with each corresponding data element; and
storing the tokenized data on a blockchain secure ledger to ensure integrity of the received data and prevent an ability to tamper with the received data.

### Claim 20 (depends on 19)

The computer program product of claim 19 wherein the network comprises a multi-tenant network, and wherein the tokenized data is split and separated on the basis of individual tenant ownership among multiple tenants, and further wherein the network comprises an enterprise scale network having storage devices storing the data in geographically distributed locations.
