IP Library Granted Patent US 12,206,759
Granted Patent B1
US 12,206,759 · App. 17/546,693 · Granted Jan 21, 2025

System and method of digital steganography

Inventors: Richard Ivey (Londonderry, NH); Piyush Kumar (Framingham, MA)
Assignee: SYSTEMS & TECHNOLOGY RESEARCH, LLC
H04L9/0631H03M13/05H04L51/063H04L51/10H04L51/52H04N1/32272H04L2209/16H04L2209/34
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 12,206,759
App. No.
17/546,693
Granted
Jan 21, 2025
Kind
B1
Abstract

A digital steganography system comprises a message sender in electronic communication with a message receiver through a social media platform. The message sender uses a compute device configured to conceal a secret digital message in the semantic components of a digitally synthesized image which is uploaded onto the social media platform and published in a social media post. As part of the message encoding process, the compute device for the message sender coverts the digital message into binary code, applies encryption and error-correction algorithms, and then implements image synthetization operations to yield the digitally synthesized image. The message receiver is provided with a compute device configured to identify the social media post, automatically download the synthesized image, and apply an inverse set of the image synthetization operations to yield binary code which is subsequently decoded and decrypted in order to extract the original covert message.

Claims (11)

1. A method of digital steganography, comprising the steps of:

(a) constructing a digital message using a compute device;

(b) converting the digital message into binary code; and

(c) synthesizing a digital image from the digital message using the compute device, the digital image having semantic components;

(d) wherein, as part of the synthetization step, the binary code is directly embedded into the semantic components of the synthesized digital image using a fully invertible image synthetization operation, the image synthetization operation including at least one artificial intelligence and machine learning algorithm for producing the synthesized image from binary code, wherein invertible normalizing flow modeling is utilized to produce the synthesized image from binary code.

2. The method as claimed in claim 1 further comprising the step of, after the conversion step and prior to the synthesizing step, digitally encrypting the binary code using the compute device to yield encrypted binary code.

3. The method as claimed in claim 2 wherein, in the encrypting step, the compute device applies an advance encryption standard (AES) encryption algorithm to the binary code to yield the encrypted binary code.

4. The method as claimed in claim 2 further comprising the step of, after the encrypting step and prior to the synthesizing step, applying error-correction algorithms to the encrypted binary code using the compute device.

5. The method as claimed in claim 4 wherein the error-correction algorithms include forward error correction algorithms and message embedding algorithms.

6. The method as claimed in claim 4 further comprising the step of, after the synthetization step, transmitting the synthesized image over a communication medium.

7. The method as claimed in claim 6 wherein, as part of the transmission step, the synthesized image is posted onto a social media platform.

Assignments (2)
CONFIRMATORY LICENSE Recorded Nov 14, 2023
From: SYSTEMS & TECHNOLOGY RESEARCH
To: GOVERNMENT OF THE UNITED STATES AS REPRESENTED BY THE SECRETARY OF THE AIR FORCE
Reel/Frame 065564/0035 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 9, 2021
From: IVEY, RICHARD; KUMAR, PIYUSH
To: SYSTEMS & TECHNOLOGY RESEARCH, LLC
Reel/Frame 058350/0091 →
Continuity (1)
Provisional Application 63129195 · Dec 22, 2020
References Cited (14)
US 5128776A · Scorse · 1992 [cited by examiner]
US 7240209B2 · Carro · 2007 [cited by examiner]
US 8872981B1 · Gish · 2014 [cited by examiner]
US 11057192B2 · Zheng · 2021 [cited by examiner]
US 20030016842A1 · Patton · 2003 [cited by examiner]
US 20110282697A1 · Fitzgerald · 2011 [cited by examiner]
US 20120311623A1 · Davis · 2012 [cited by examiner]
US 20130091564A1 · Fitzgerald · 2013 [cited by examiner]
US 20140200929A1 · Fitzgerald · 2014 [cited by examiner]
US 20190356476A1 · Zheng · 2019 [cited by examiner]
Hayes, Jamie, and George Danezis. “Generating steganographic images via adversarial training.” Advances in neural information processing systems 30 (2017) (Year: 2017). [cited by examiner]
Zhang Z, Fu G, Ni R, Liu J, Yang X. A generative method for steganography by cover synthesis with auxiliary semantics. Tsinghua Science and Technology. Jan. 13, 2020;25(4):516-27 (Year: 2020). [cited by examiner]
Duan X, Liu N, Gou M, Wang W, Qin C. SteganoCNN: Image steganography with generalization ability based on convolutional neural network. Entropy. Oct. 8, 2020;22(10):1140 (Year: 2020). [cited by examiner]
NPL Search Terms (Year: 2024). [cited by examiner]
Cited By (2)
US 12,526,259 US 12,585,793