Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection
Progress in Deep Learning (DL) has introduced alternative methods for tackling complex challenges, such as the steganalysis of spatial domain images, where Convolutional Neural Networks (CNNs) are employed. In recent years, various CNN architectures have emerged, enhancing the precision of detecting...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10323088/ |
_version_ | 1797448853513830400 |
---|---|
author | Ntivuguruzwa Jean De La Croix Tohari Ahmad Fengling Han |
author_facet | Ntivuguruzwa Jean De La Croix Tohari Ahmad Fengling Han |
author_sort | Ntivuguruzwa Jean De La Croix |
collection | DOAJ |
description | Progress in Deep Learning (DL) has introduced alternative methods for tackling complex challenges, such as the steganalysis of spatial domain images, where Convolutional Neural Networks (CNNs) are employed. In recent years, various CNN architectures have emerged, enhancing the precision of detecting steganographic images. Nevertheless, current CNNs encounter challenges related to the inadequate quality and quantity of available datasets, high imperceptibility of low payload capacities, and suboptimal feature learning processes. This paper proposes an enhanced secret data detection approach with a CNN architecture that includes convolutional, depth-wise, separable, pooling, and spatial dropout layers. An improved fuzzy Prewitt approach is employed for pre-processing the images prior to being fed into CNN to address the issues of low payload capacity detection and dataset quality and quantity in learnability of the image features. Experimental results, which achieved an overall accuracy and F1-score of 99.6 and 99.3 per cent, respectively, to detect a steganographic payload of 0.5 bpp hidden with Wavelet Obtained Weights (WOW), show a significant outperformance over the state-of-the-art methods. |
first_indexed | 2024-03-09T14:16:26Z |
format | Article |
id | doaj.art-1f561bae68ff44668ace6e2af8f47fa1 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-09T14:16:26Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-1f561bae68ff44668ace6e2af8f47fa12023-11-29T00:01:12ZengIEEEIEEE Access2169-35362023-01-011113100113101610.1109/ACCESS.2023.333465010323088Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge DetectionNtivuguruzwa Jean De La Croix0https://orcid.org/0000-0001-5249-1241Tohari Ahmad1https://orcid.org/0000-0002-3390-0756Fengling Han2https://orcid.org/0000-0001-8756-7197Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaDepartment of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaSchool of Computing Technologies, RMIT University, Melbourne, VIC, AustraliaProgress in Deep Learning (DL) has introduced alternative methods for tackling complex challenges, such as the steganalysis of spatial domain images, where Convolutional Neural Networks (CNNs) are employed. In recent years, various CNN architectures have emerged, enhancing the precision of detecting steganographic images. Nevertheless, current CNNs encounter challenges related to the inadequate quality and quantity of available datasets, high imperceptibility of low payload capacities, and suboptimal feature learning processes. This paper proposes an enhanced secret data detection approach with a CNN architecture that includes convolutional, depth-wise, separable, pooling, and spatial dropout layers. An improved fuzzy Prewitt approach is employed for pre-processing the images prior to being fed into CNN to address the issues of low payload capacity detection and dataset quality and quantity in learnability of the image features. Experimental results, which achieved an overall accuracy and F1-score of 99.6 and 99.3 per cent, respectively, to detect a steganographic payload of 0.5 bpp hidden with Wavelet Obtained Weights (WOW), show a significant outperformance over the state-of-the-art methods.https://ieeexplore.ieee.org/document/10323088/Convolutional neural networksfuzzy logicinformation securitynetwork infrastructurenetwork securityspatial domain |
spellingShingle | Ntivuguruzwa Jean De La Croix Tohari Ahmad Fengling Han Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection IEEE Access Convolutional neural networks fuzzy logic information security network infrastructure network security spatial domain |
title | Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection |
title_full | Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection |
title_fullStr | Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection |
title_full_unstemmed | Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection |
title_short | Enhancing Secret Data Detection Using Convolutional Neural Networks With Fuzzy Edge Detection |
title_sort | enhancing secret data detection using convolutional neural networks with fuzzy edge detection |
topic | Convolutional neural networks fuzzy logic information security network infrastructure network security spatial domain |
url | https://ieeexplore.ieee.org/document/10323088/ |
work_keys_str_mv | AT ntivuguruzwajeandelacroix enhancingsecretdatadetectionusingconvolutionalneuralnetworkswithfuzzyedgedetection AT tohariahmad enhancingsecretdatadetectionusingconvolutionalneuralnetworkswithfuzzyedgedetection AT fenglinghan enhancingsecretdatadetectionusingconvolutionalneuralnetworkswithfuzzyedgedetection |