Document Type : Original Research Paper

Author

• V. Sabeti

Department of Computer Engineering, Faculty of Engineerning, Alzahra University, Tehran, Iran.

Abstract

Background and Objectives: Steganalysis is the study of detecting messages hidden using steganography. Most steganalysis techniques, known as blind steganalysis, focus on extracting and classifying various statistical features from images. Consequently, researchers continually seek to improve the accuracy of blind detection methods. The current study proposes a blind steganalysis technique based on overlapping blocks.
Methods: The proposed method began by decomposing the image into identically sized overlapping blocks, then extracted a feature vector from each block. Subsequently, a tree-structured hierarchical clustering technique was used to partition blocks into multiple classes based on extracted features, and a classifier was trained for each class to determine whether a block is from a cover or stego image. The block decomposition process was repeated for each test image, and a classifier was selected based on the block class to make a decision for each block. Furthermore, the majority vote rule was utilized to determine whether the test image is a cover or stego image.
Results: The proposed method was evaluated using the INRIA and BOSSbase datasets. Several parameters, including the number of block classes, feature extraction method, block size, and number and block overlapping level, affected the performance of the proposed method. The optimal block size was 64 × 64 by 32 steps, and the number of block classes was set to 16. WOW, S-UNIWARD, PQ, and nsF5 were the steganographic methods employed to evaluate the proposed method. Experimental results indicated that using overlapping instead of non-overlapping blocks increased the detection of data embedded in both the spatial and Joint Photographic Experts Group (JPEG) domains by an average of over 9%. In addition, the proposed method's accuracy in detecting the S-UNIWARD method was comparable to that of other deep learning-based steganalysis techniques.
Conclusion: The concept of using overlapping blocks improves the efficiency of blind steganalysis by providing the benefit of additional and larger blocks. One of the main advantages of the proposed method is comparable detection accuracy and less computational complexity than recent deep learning-based steganalysis techniques.

Keywords

• Steganalysis
• Steganography
• Blind Steganalysis
• Spatial Steganograph
• JPEG Steganography

20.1001.1.23223952.2023.11.2.3.5

Main Subjects

• Information Hiding

Open Access

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/

Publisher’s Note

JECEI Publisher remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Publisher

Shahid Rajaee Teacher Training University