Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Dynamic YOLO-Based Sequence-Matching Model for Efficient Coverless Image Steganography

Jiajun Liu, Lina Tan, Zhili Zhou, Yi Li, Peng Chen

TL;DR

The paper tackles the challenge of coverless image steganography with limited image libraries by proposing a dynamic, substring-based sequence-matching model that leverages YOLO-based object detection to assign scrambling factors to images. A four-level data architecture, built through preprocessing steps (mapping dictionary creation, sequence key distribution, and scrambling factor generation), supports efficient, secure hiding and extraction of secret data via per-receiver sequence keys and AES-encrypted keys. The method achieves about $19$ bits per image with roughly $200$ cover images and demonstrates strong robustness to geometric and noise attacks, while substantially reducing database size compared to prior mapping-rule approaches. These contributions enable scalable, secure coverless steganography with practical hiding capacity and resilience, though future work aims to further enhance capacity while maintaining efficiency and security.

Abstract

Many existing coverless steganography methods establish a mapping relationship between cover images and hidden data. There exists an issue that the number of images stored in the database grows exponentially as the steganographic capacity rises. The need for a high steganographic capacity makes it challenging to build an image database. To improve the image library utilization and anti-attack capability of the steganography system, we present an efficient coverless scheme based on dynamically matched substrings. YOLO is employed for selecting optimal objects, and a mapping dictionary is established between these objects and scrambling factors. With the aid of this dictionary, each image is effectively assigned to a specific scrambling factor, which is used to scramble the receiver's sequence key. To achieve sufficient steganography capability based on a limited image library, all substrings of the scrambled sequences hold the potential to hide data. After completing the secret information matching, the ideal number of stego images will be obtained from the database. According to experimental results, this technology outperforms most previous works on data load, transmission security, and hiding capacity. Under typical geometric attacks, it can recover 79.85\% of secret information on average. Furthermore, only approximately 200 random images are needed to meet a capacity of 19 bits per image.

A Dynamic YOLO-Based Sequence-Matching Model for Efficient Coverless Image Steganography

TL;DR

The paper tackles the challenge of coverless image steganography with limited image libraries by proposing a dynamic, substring-based sequence-matching model that leverages YOLO-based object detection to assign scrambling factors to images. A four-level data architecture, built through preprocessing steps (mapping dictionary creation, sequence key distribution, and scrambling factor generation), supports efficient, secure hiding and extraction of secret data via per-receiver sequence keys and AES-encrypted keys. The method achieves about bits per image with roughly cover images and demonstrates strong robustness to geometric and noise attacks, while substantially reducing database size compared to prior mapping-rule approaches. These contributions enable scalable, secure coverless steganography with practical hiding capacity and resilience, though future work aims to further enhance capacity while maintaining efficiency and security.

Abstract

Many existing coverless steganography methods establish a mapping relationship between cover images and hidden data. There exists an issue that the number of images stored in the database grows exponentially as the steganographic capacity rises. The need for a high steganographic capacity makes it challenging to build an image database. To improve the image library utilization and anti-attack capability of the steganography system, we present an efficient coverless scheme based on dynamically matched substrings. YOLO is employed for selecting optimal objects, and a mapping dictionary is established between these objects and scrambling factors. With the aid of this dictionary, each image is effectively assigned to a specific scrambling factor, which is used to scramble the receiver's sequence key. To achieve sufficient steganography capability based on a limited image library, all substrings of the scrambled sequences hold the potential to hide data. After completing the secret information matching, the ideal number of stego images will be obtained from the database. According to experimental results, this technology outperforms most previous works on data load, transmission security, and hiding capacity. Under typical geometric attacks, it can recover 79.85\% of secret information on average. Furthermore, only approximately 200 random images are needed to meet a capacity of 19 bits per image.
Paper Structure (20 sections, 1 equation, 3 figures, 6 tables)

This paper contains 20 sections, 1 equation, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. The proposed method
  3. Overall Framework
  4. Preprocessing
  5. Mapping Dictionary Creation
  6. Sequence Key Distribution
  7. Scrambling Factor Generation
  8. Building Data Architecture
  9. Information Hiding
  10. Information Extraction
  11. Experiments and Analysis
  12. Hiding Capacity
  13. Capacity Test of Our Method
  14. Comparison of Capacity
  15. Database Size
  16. ...and 5 more sections

Figures (3)

  • Figure 1: Flowchart of The Coverless Image Steganography Algorithm
  • Figure 2: The Data Architecture of Image Database
  • Figure 3: Process Chart for Information Extraction