IP Library Granted Patent US 10,755,375
Granted Patent B2
US 10,755,375 · App. 15/903,888 · Granted Aug 25, 2020

Systems and methods for steganography based on text fonts

Inventors: Changxi Zheng (New York, NY); Chang Xiao (New York, NY); Cheng Zhang (New York, NY)
G06T1/0021G06K9/6828G06T1/0028H03M13/159G06T2201/0061G06T2201/0062H03M13/09
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 10,755,375
App. No.
15/903,888
Granted
Aug 25, 2020
Kind
B2
Abstract

Disclosed are methods, systems, devices, apparatus, media, and other implementations, including a method that includes obtaining input visual data comprising a sequence of symbols, selected from a symbol set, with each of the symbols associated with a glyph representation. The method also includes obtaining a code message comprising code message symbols, and modifying at least one of the symbols of the input visual data to a different glyph representation associated with a respective at least one of the code message symbols to generate, at a first time instance, a resultant coded visual data.

Claims (48)

1. A method comprising:

obtaining input visual data comprising a sequence of symbols, selected from a symbol set, with each of the symbols associated with a glyph representation;

obtaining a code message comprising code message symbols;

modifying at least one of the symbols of the input visual data to a different glyph representation associated with a respective at least one of the code message symbols to generate, at a first time instance, a resultant coded visual data, wherein modifying the at least one of the symbols comprises modifying the at least one of the symbols with the different glyph representation associated with the respective at least one of the code message symbols according to a codebook comprising, for each available symbol from the symbol set, a corresponding set of glyphs associated with respective ones of available code message symbols; and

communicating, at a second time instance subsequent to the first time instance, the generated resultant coded visual data to a remote device, wherein the communicated generated resultant coded visual data is decoded at the remote device according to a decoding process that includes:

computing, for each of the modified at least one of the symbols with the different glyph representation, distance metrics between the at least one of the symbols with the different glyph representation and each glyph in the corresponding set of glyphs in the codebook; and

determining, based on the computed distance metrics, the respective code message symbol corresponding to the each of modified at least one of the symbols with the different glyph representation.

2. The method of claim 1 , further comprising:

determining a font associated with the sequence of symbols; and

selecting the codebook from a plurality of codebooks based on the determined font.

3. The method of claim 1 , wherein the codebook defines a set of error correcting codes.

4. The method of claim 3 , wherein the set of error correcting codes comprise codes based on the Chinese Reminder Theorem (CRT).

5. The method of claim 1 , wherein the decoding process at the remote device further includes:

extracting from the communicated generated resultant coded visual data the each of the modified at least one of the symbols with the different glyph representation; and

aligning the extracted each of the modified at least one of the symbols with the different glyph representation with symbols in the codebook, the aligning being based on outlines of the extracted each of the modified at least one of the symbols and of the symbols in the codebook.

6. The method of claim 1 , wherein determining, based on the computed distance metrics, the code message symbol, comprises:

selecting a decoded glyph associated with a minimum distance metrics between the each of modified at least one of the symbols and possible decoded glyph candidates for the each of modified at least one of the symbols.

7. The method of claim 1 , wherein the code message comprises a sequence of integers representative of a plain text message encoded into the sequence of integers.

8. A system comprising:

at least one processor; and

storage media comprising computer instructions that, when executed on the at least one processor, cause operations comprising:

obtaining input visual data comprising a sequence of symbols, selected from a symbol set, with each of the symbols associated with a glyph representation;

obtaining a code message comprising code message symbols; and

modifying at least one of the symbols of the input visual data to a different glyph representation associated with a respective at least one of the code message symbols to generate, at a first time instance, a resultant coded visual data, wherein modifying the at least one of the symbols comprises modifying the at least one of the symbols with the different glyph representation associated with the respective at least one of the code message symbols according to a codebook comprising, for each available symbol from the symbol set, a corresponding set of glyphs associated with respective ones of available code message symbols; and

communicating, at a second time instance subsequent to the first time instance, the generated resultant coded visual data to a remote device, wherein the communicated generated resultant coded visual data is decoded at the remote device according to a decoding process that includes:

computing, for each of the modified at least one of the symbols with the different glyph representation, distance metrics between the at least one of the symbols with the different glyph representation and each glyph in the corresponding set of glyphs in the codebook; and

determining, based on the computed distance metrics, the respective code message symbol corresponding to the each of modified at least one of the symbols with the different glyph representation.

9. The system of claim 8 , wherein the operations further comprise:

determining a font associated with the sequence of symbols; and

selecting the codebook from a plurality of codebooks based on the determined font.

10. The system of claim 8 , wherein the codebook defines a set of error correcting codes.

11. The system of claim 10 , wherein the set of error correcting codes comprise codes based on the Chinese Reminder Theorem (CRT).

12. The system of claim 8 , wherein the decoding process at the remote device further includes:

extracting from the communicated generated resultant coded visual data the each of the modified at least one of the symbols with the different glyph representation; and

aligning the extracted each of the modified at least one of the symbols with the different glyph representation with symbols in the codebook, the aligning being based on outlines of the extracted each of the modified at least one of the symbols and of the symbols in the codebook.

13. The system of claim 8 , wherein determining, based on the computed distance metrics, the code message symbol, comprises:

selecting a decoded glyph associated with a minimum distance metrics between the each of modified at least one of the symbols and possible decoded glyph candidates for the each of modified at least one of the symbols.

14. The system of claim 8 , wherein the code message comprises a sequence of integers representative of a plain text message encoded into the sequence of integers.

15. Non-transitory computer readable media comprising computer instructions executable on a processor-based device to:

obtain input visual data comprising a sequence of symbols, selected from a symbol set, with each of the symbols associated with a glyph representation;

obtain a code message comprising code message symbols;

modify at least one of the symbols of the input visual data to a different glyph representation associated with a respective at least one of the code message symbols to generate, at a first time instance, a resultant coded visual data, wherein the instructions to modify the at least one of the symbols include one or more instructions to modify the at least one of the symbols with the different glyph representation associated with the respective at least one of the code message symbols according to a codebook comprising, for each available symbol from the symbol set, a corresponding set of glyphs associated with respective ones of available code message symbols; and

communicate, at a second time instance subsequent to the first time instance, the generated resultant coded visual data to a remote device, wherein the communicated generated resultant coded visual data is decoded at the remote device according to a decoding process that includes:

computing, for each of the modified at least one of the symbols with the different glyph representation, distance metrics between the at least one of the symbols with the different glyph representation and each glyph in the corresponding set of glyphs in the codebook; and

determining, based on the computed distance metrics, the respective code message symbol corresponding to the each of modified at least one of the symbols with the different glyph representation.

16. The computer readable media of claim 15 , further comprising one or more instructions to:

determine a font associated with the sequence of symbols; and

select the codebook from a plurality of codebooks based on the determined font.

Assignments (2)
CONFIRMATORY LICENSE Recorded Dec 7, 2022
From: COLUMBIA UNIVERSITY NEW YORK MORNINGSIDE
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 062009/0156 →
CONFIRMATORY LICENSE Recorded Oct 21, 2020
From: COLUMBIA UNIVERSITY
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 054167/0741 →
Continuity (2)
Provisional Application 62463118 · Feb 24, 2017
Related Publication 20180247386A1 · Aug 30, 2018