# US 2025/0165649 A1 · Attribute-based encryption for selective document content protection

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

- Number: US 2025/0165649 A1
- Document ID: US20250165649A1
- Status: Published application
- Kind: A1
- Application number: 18/950,165
- Filed: 2024-11-17
- Published: 2025-05-22
- Earliest claimed: 2023-11-16
- Assignees: NTT Research, Inc.
- Applicants: NTT Research, Inc.; NTT Belgium NV/SA; NTT DATA Services Federal Government LLC
- Inventors: Nat Bongiovanni; Jean-Philippe Cabay; Takashi Goto; Pascal Mathis; Farid Shahlavi; Tim Weidman; Paul Yu
- Web page: https://patentgrep.com/patent/US20250165649A1

## CPC

- G06F 21/6209: {to a single file or object, e.g. in a secure envelope, encrypted and accessed using a key, or with access control rules appended to the object itself}
- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F 21/602: {Providing cryptographic facilities or services}
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 40/205: Parsing
- G06N 3/045: Combinations of networks
- G06T 7/11: Region-based segmentation
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 10/764: using classification, e.g. of video objects
- H04L 9/0819: {Key transport or distribution, i.e. key establishment techniques where one party creates or otherwise obtains a secret value, and securely transfers it to the other(s) (network architectures or network communication protocols for key distribution in a packet data network H04L63/062)}
- H04L 9/0847: {involving identity based encryption [IBE] schemes}
- H04L 9/0894: {Escrow, recovery or storing of secret information, e.g. secret key escrow or cryptographic key storage}
- H04L 9/3073: {involving pairings, e.g. identity based encryption [IBE], bilinear mappings or bilinear pairings, e.g. Weil or Tate pairing}
- H04L 63/0428: {wherein the data content is protected, e.g. by encrypting or encapsulating the payload}
- G06T 2207/20084: Artificial neural networks [ANN]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

The present disclosure provides a method for securing document content. A document security manager receives a digital document containing original text and image content. The original text content is processed to identify text portions by parsing annotations, analyzing proximate text, extracting content within the determined scope, and determining encryption attributes. The original image content is processed to identify image portions by detecting user-defined selections or employing a neural network to identify sensitive objects. Encrypt content requests are generated including the identified text and image portions with associated attributes and metadata. The requests are transmitted to a cryptographic engine, which returns encrypted content. A partially encrypted document is built by replacing original content with masking symbols, applying visual obfuscation, embedding encrypted content as metadata, and updating document properties to indicate encrypted content.

## Claims

### Claim 1

A method for securing document content, comprising:
receiving, by a document security manager implemented on a computing device, a digital document containing original text content and original image content;
processing the original text content to identify text content portions by:
parsing the document to locate in-line text annotations,
analyzing proximate text to determine the scope of each annotation,
extracting text content within the determined scope, and
determining encryption attributes for an attribute-based encryption scheme based on the in-line text annotations;
processing the original image content to identify image portions by:
detecting user-defined selections of image regions through a graphical interface, or
employing a trained neural network to automatically identify and classify sensitive objects within the images;
generating one or more encrypt content requests, the one or more requests including:
the identified text portions with their associated encryption attributes,
the identified image portions with corresponding bounding box coordinates, and
metadata specifying the encryption schemes to be applied;
transmitting the encrypt content requests to a cryptographic engine via a secure communication channel;
receiving, from the cryptographic engine, encrypted text content for the text portions and encrypted image content for the image portions, wherein the cryptographic engine applies an attribute-based encryption scheme to the text portions and image portions; and
building a partially encrypted document by:
replacing original text content with masking symbols,
programmatically adjusting the masking symbol width to maintain document layout and formatting,
applying visual obfuscation techniques to the original image content based on sensitivity levels,
embedding the encrypted text and image content as metadata within the document structure, and
updating document properties to indicate the presence of encrypted content.

### Claim 2 (depends on 1)

The method of claim 1, wherein the attribute-based encryption scheme utilizes a ciphertext-policy attribute-based encryption (CP-ABE) algorithm, and wherein the encryption attributes for text portions include:
access policy expressions defining combinations of user attributes required for decryption,
time-based constraints specifying validity periods for decryption keys, and
hierarchical attribute structures representing organizational roles and clearance levels.

### Claim 3 (depends on 1)

The method of claim 1, wherein processing the original image content further comprises:
segmenting the image into multiple regions using a convolutional neural network,
extracting feature vectors for each segmented region using a pre-trained deep learning model,
classifying the sensitivity level of each region based on the extracted features, and
generating encryption attributes for each region based on its classified sensitivity level and content type.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
generating a decryption key request based on authenticated user attributes;
transmitting the decryption key request to a key management server;
receiving a decryption key from the key management server, wherein the decryption key is derived from the user's attribute set and a master secret key;
selectively decrypting portions of the document using the received decryption key; and
rendering a partially decrypted version of the document with authorized content visible and unauthorized content remaining obfuscated.

### Claim 5 (depends on 1)

The method of claim 1, wherein the cryptographic engine implements a multi-authority attribute-based encryption scheme, and wherein generating the encrypt content requests further comprises:
assigning each text and image portion to one or more attribute authorities based on the content type and sensitivity;
generating separate encryption policies for each assigned authority; and
including authority identifiers and corresponding encryption policies in the encrypt content requests.

### Claim 6 (depends on 1)

The method of claim 1, wherein building the partially encrypted document further comprises:
generating a document-specific symmetric key;
encrypting the symmetric key using the attribute-based encryption scheme with a master public key;
encrypting the text and image portions using the symmetric key;
embedding the encrypted symmetric key and the encrypted content within the document structure; and
including key recovery information that allows authorized users to reconstruct decryption keys using their attribute credentials and a subset of master private key shares.

### Claim 7 (depends on 1)

The method of claim 1, wherein the digital document comprises a video file, and wherein processing the original image content further comprises:
extracting individual frames from the video file;
analyzing the extracted frames to identify sensitive objects or regions;
generating temporal bounding boxes to track the identified sensitive objects or regions across multiple frames;
applying the visual obfuscation techniques to the sensitive objects or regions within each affected frame; and
reconstructing the video file with the obfuscated frames while maintaining the original video format and playback characteristics.

### Claim 8 (depends on 1)

The method of claim 1, wherein processing the original text content further comprises:
identifying text decorations within the document, including bold, italic, underline, strikethrough, or color formatting;
associating the identified text decorations with corresponding sensitivity levels or encryption attributes; and
adjusting the encryption attributes for text portions based on the associated text decorations.

### Claim 9

A system for securing document content, comprising:
a document security manager implemented on a computing device, the document security manager configured to:
receive a digital document containing original text content and original image content;
process the original text content to identify text content portions by:
parsing the document to locate in-line text annotations,
analyzing proximate text to determine the scope of each annotation,
extracting text content within the determined scope, and
determining encryption attributes for an attribute-based encryption scheme based on the in-line text annotations;
process the original image content to identify image portions by:
detecting user-defined selections of image regions through a graphical interface, or
employing a trained neural network to automatically identify and classify sensitive objects within the images;
generate one or more encrypt content requests, the one or more requests including:
the identified text portions with their associated encryption attributes,
the identified image portions with corresponding bounding box coordinates, and
metadata specifying the encryption schemes to be applied;
transmit the encrypt content requests to a cryptographic engine via a secure communication channel;
receive, from the cryptographic engine, encrypted text content for the text portions and encrypted image content for the image portions, wherein the cryptographic engine applies an attribute-based encryption scheme to the text portions and image portions; and
build a partially encrypted document by:
replacing original text content with masking symbols,
programmatically adjusting the masking symbol width to maintain document layout and formatting,
applying visual obfuscation techniques to the original image content based on sensitivity levels,
embedding the encrypted text and image content as metadata within the document structure, and
updating document properties to indicate the presence of encrypted content.

### Claim 10 (depends on 9)

The system of claim 9, wherein the attribute-based encryption scheme utilizes a ciphertext-policy attribute-based encryption (CP-ABE) algorithm, and wherein the encryption attributes for text portions include:
access policy expressions defining combinations of user attributes required for decryption,
time-based constraints specifying validity periods for decryption keys, and
hierarchical attribute structures representing organizational roles and clearance levels.

### Claim 11 (depends on 9)

The system of claim 9, wherein processing the original image content further comprises:
segmenting the image into multiple regions using a convolutional neural network,
extracting feature vectors for each segmented region using a pre-trained deep learning model,
classifying the sensitivity level of each region based on the extracted features, and
generating encryption attributes for each region based on its classified sensitivity level and content type.

### Claim 12 (depends on 9)

The system of claim 9, wherein the document security manager is further configured to:
generate a decryption key request based on authenticated user attributes;
transmit the decryption key request to a key management server;
receive a decryption key from the key management server, wherein the decryption key is derived from the user's attribute set and a master secret key;
selectively decrypt portions of the document using the received decryption key; and
render a partially decrypted version of the document with authorized content visible and unauthorized content remaining obfuscated.

### Claim 13 (depends on 9)

The system of claim 9, wherein the cryptographic engine implements a multi-authority attribute-based encryption scheme, and wherein generating the encrypt content requests further comprises:
assigning each text and image portion to one or more attribute authorities based on the content type and sensitivity;
generating separate encryption policies for each assigned authority; and
including authority identifiers and corresponding encryption policies in the encrypt content requests.

### Claim 14 (depends on 9)

The system of claim 9, wherein building the partially encrypted document further comprises:
generating a document-specific symmetric key;
encrypting the symmetric key using the attribute-based encryption scheme with a master public key;
encrypting the text and image portions using the symmetric key;
embedding the encrypted symmetric key and the encrypted content within the document structure; and
including key recovery information that allows authorized users to reconstruct decryption keys using their attribute credentials and a subset of master private key shares.

### Claim 15 (depends on 9)

The system of claim 9, wherein the digital document comprises a video file, and wherein processing the original image content further comprises:
extracting individual frames from the video file;
analyzing the extracted frames to identify sensitive objects or regions;
generating temporal bounding boxes to track the identified sensitive objects or regions across multiple frames;
applying the visual obfuscation techniques to the sensitive objects or regions within each affected frame; and
reconstructing the video file with the obfuscated frames while maintaining the original video format and playback characteristics.

### Claim 16

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for securing document content, the method comprising:
receiving a digital document containing original text content and original image content;
processing the original text content to identify text content portions by:
parsing the document to locate in-line text annotations,
analyzing proximate text to determine the scope of each annotation,
extracting text content within the determined scope, and
determining encryption attributes for an attribute-based encryption scheme based on the in-line text annotations;
processing the original image content to identify image portions by:
detecting user-defined selections of image regions through a graphical interface, or
employing a trained neural network to automatically identify and classify sensitive objects within the images;
generating one or more encrypt content requests, the one or more requests including:
the identified text portions with their associated encryption attributes,
the identified image portions with corresponding bounding box coordinates, and
metadata specifying the encryption schemes to be applied;
transmitting the encrypt content requests to a cryptographic engine via a secure communication channel;
receiving, from the cryptographic engine, encrypted text content for the text portions and encrypted image content for the image portions, wherein the cryptographic engine
applies an attribute-based encryption scheme to the text portions and image portions; and
building a partially encrypted document by:
replacing original text content with masking symbols,
programmatically adjusting the masking symbol width to maintain document layout and formatting,
applying visual obfuscation techniques to the original image content based on sensitivity levels,
embedding the encrypted text and image content as metadata within the document structure, and
updating document properties to indicate the presence of encrypted content.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the attribute-based encryption scheme utilizes a ciphertext-policy attribute-based encryption (CP-ABE) algorithm, and wherein the encryption attributes for text portions include:
access policy expressions defining combinations of user attributes required for decryption,
time-based constraints specifying validity periods for decryption keys, and
hierarchical attribute structures representing organizational roles and clearance levels.

### Claim 18 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein processing the original image content further comprises:
segmenting the image into multiple regions using a convolutional neural network,
extracting feature vectors for each segmented region using a pre-trained deep learning model,
classifying the sensitivity level of each region based on the extracted features, and
generating encryption attributes for each region based on its classified sensitivity level and content type.

### Claim 19 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the method further comprises:
generating a decryption key request based on authenticated user attributes;
transmitting the decryption key request to a key management server;
receiving a decryption key from the key management server, wherein the decryption key is derived from the user's attribute set and a master secret key;
selectively decrypting portions of the document using the received decryption key; and
rendering a partially decrypted version of the document with authorized content visible and unauthorized content remaining obfuscated.

### Claim 20 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the cryptographic engine implements a multi-authority attribute-based encryption scheme, and wherein generating the encrypt content requests further comprises:
assigning each text and image portion to one or more attribute authorities based on the content type and sensitivity;
generating separate encryption policies for each assigned authority; and
including authority identifiers and corresponding encryption policies in the encrypt content requests.
