Steganography Detection System for Cyber Forensics

Authors: Rhutu Abhijeet Khire, Prachi Krishnat Jadhav, Harshada Santosh Barge, Prof. Mujawar S. A.

DOI Link: https://doi.org/10.22214/ijraset.2026.79830

Abstract

The swift expansion of digital media has led to steganography becoming a significant challenge in cyber forensics, allowing malicious individuals to hide sensitive information within seemingly harmless carrier files. Steganography is defined as the practice of embedding confidential data within another data stream, enabling it to be sent to its destination without arousing suspicion. Among the various carrier types, images are most commonly used due to their high data capacity and widespread availability. Several techniques have been developed for embedding information within digital images, with the Least Significant Bit (LSB) method being one of the most widely adopted. This paper presents the technique for detecting steganography, allowing forensic investigators to uncover and scrutinize digital assets. The proposed method utilizes statistical analysis approaches, including Chi-square and RS steganalysis, to automatically detect concealed payloads. Experimental results demonstrate that the approach achieves high accuracy across diverse range of datasets, effectively distinguishing between “clean” and “stego” images, even at low embedding rates are used.

Introduction

The text explains the importance of steganography, a technique used to hide secret information inside digital media such as images, audio, or video so that the existence of the message remains unnoticed. It discusses image-based steganography, especially the Least Significant Bit (LSB) method, where secret data is embedded into the least important bits of image pixels with minimal visible distortion. The text highlights the trade-off among data capacity, robustness, and imperceptibility, known as Johnson’s Magic Triangle Model. While LSB steganography is simple and widely used, it is vulnerable to detection through steganalysis techniques such as Chi-Square analysis and RS (Regular-Singular) steganalysis. Chi-Square analysis detects statistical irregularities in pixel distributions, whereas RS steganalysis examines structural changes in pixel groups for more accurate detection. The document also reviews existing research on advanced LSB methods designed to improve hiding capacity and resist detection. Finally, it presents a proposed cyber forensic steganography detection system that combines statistical and structural analysis methods to identify hidden data in digital images through stages such as image acquisition, preprocessing, feature extraction, and forensic analysis.

Conclusion

The Steganography Detection System was effectively developed and implemented to identify concealed information within digital images, addressing the pressing need for automated analysis using statistical and analytical methods in the realm of cyber forensics amid the rising prevalence of covert communication and data hiding techniques. This approach employs multiple detection methods, including Least Significant Bit (LSB) analysis, Chi-square testing, and RS steganalysis, to evaluate pixel-level alterations and identify a typical patterns resulting and data embedding, thereby enhancing detection accuracy and reducing false positives, while the incorporation of a risk score mechanism further aids in clearly indicating the probability of concealed data and simplifying result interpretation. The initiative emphasizes usability by providing a straightforward interface for users to input images and receive prompt analysis results, thereby reducing the necessity for manual inspections, conserving time, and enhancing efficiency in cyber forensic investigations; furthermore, the system is meant to be scalable and may be enhanced with modern technologies such as machine learning to increase its performance in the future. The steganography detection system addresses the shortcomings of current methodologies by providing a dependable, efficient, and automated means of uncovering concealed information, thereby enhancing cybersecurity, aiding in digital evidence analysis, and mitigating the potential misuse of steganography for harmful intents.

References

[1] Wu, Da-Chun, and Wen-Hsiang Tsai. \"A steganographic method for images by pixel-value differencing.\" Pattern Recognition Letters 24, no. 9 (2003): 1613-1626. [2] Johnson, Neil F., and Sushil Jajodia. \"Exploring steganography: Seeing the unseen.\" Computer 31, no. 2 (1998): 26-34. [3] Fridrich, J., Goljan, M., Du, R.: Steganalysis based on JPEG compatibility. In Tescher, A.G., Vasudev, B., Bove, Jr, V.M., eds.: Multimedia Systems and Applications IV. Volume 4518 of Proc. SPIE. (2002) 275–280 [4] C.-K. Chan and M. Cheng, “Hiding data in images by simple LSB substitution,” Pattern Recognition, vol. 37, no. 3, pp. 469-474, 2004. [5] T. Morkel, J.H.P. Eloff, and M.S. Oliver, “An overview of image steganography,” in Proc. ISSA, pp. 1-11, 2.

Copyright

Copyright © 2026 Rhutu Abhijeet Khire, Prachi Krishnat Jadhav, Harshada Santosh Barge, Prof. Mujawar S. A.. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download Paper

Paper Id : IJRASET79830

Publish Date : 2026-04-09

ISSN : 2321-9653

Publisher Name : IJRASET

DOI Link : Click Here