Detection of Image Steganography Using Deep Learning and Ensemble Classifiers
In this article, the problem of detecting JPEG images, which have been steganographically manipulated, is discussed. The performance of employing various shallow and deep learning algorithms in image steganography detection is analyzed. The data, images from the BOSS database, were used with informa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/10/1565 |
| _version_ | 1797500282173652992 |
|---|---|
| author | Mikołaj Płachta Marek Krzemień Krzysztof Szczypiorski Artur Janicki |
| author_facet | Mikołaj Płachta Marek Krzemień Krzysztof Szczypiorski Artur Janicki |
| author_sort | Mikołaj Płachta |
| collection | DOAJ |
| description | In this article, the problem of detecting JPEG images, which have been steganographically manipulated, is discussed. The performance of employing various shallow and deep learning algorithms in image steganography detection is analyzed. The data, images from the BOSS database, were used with information hidden using three popular steganographic algorithms: JPEG universal wavelet relative distortion (J-Uniward), nsF5, and uniform embedding revisited distortion (UERD) at two density levels. Various feature spaces were verified, with the discrete cosine transform residuals (DCTR) and the Gabor filter residuals (GFR) yielding best results. Almost perfect detection was achieved for the nsF5 algorithm at 0.4 bpnzac density (99.9% accuracy), while the detection of J-Uniward at 0.1 bpnzac density turned out to be hardly possible (max. 56.3% accuracy). The ensemble classifiers turned out to be an encouraging alternative to deep learning-based detection methods. |
| first_indexed | 2024-03-10T03:59:40Z |
| format | Article |
| id | doaj.art-1f20a5a320a842a99e87ae1ecf04b303 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:59:40Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-1f20a5a320a842a99e87ae1ecf04b3032023-11-23T10:47:03ZengMDPI AGElectronics2079-92922022-05-011110156510.3390/electronics11101565Detection of Image Steganography Using Deep Learning and Ensemble ClassifiersMikołaj Płachta0Marek Krzemień1Krzysztof Szczypiorski2Artur Janicki3Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, PolandFaculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, PolandFaculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, PolandFaculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, PolandIn this article, the problem of detecting JPEG images, which have been steganographically manipulated, is discussed. The performance of employing various shallow and deep learning algorithms in image steganography detection is analyzed. The data, images from the BOSS database, were used with information hidden using three popular steganographic algorithms: JPEG universal wavelet relative distortion (J-Uniward), nsF5, and uniform embedding revisited distortion (UERD) at two density levels. Various feature spaces were verified, with the discrete cosine transform residuals (DCTR) and the Gabor filter residuals (GFR) yielding best results. Almost perfect detection was achieved for the nsF5 algorithm at 0.4 bpnzac density (99.9% accuracy), while the detection of J-Uniward at 0.1 bpnzac density turned out to be hardly possible (max. 56.3% accuracy). The ensemble classifiers turned out to be an encouraging alternative to deep learning-based detection methods.https://www.mdpi.com/2079-9292/11/10/1565steganographymachine learningimage processingBOSS databaseensemble classifierdeep learning |
| spellingShingle | Mikołaj Płachta Marek Krzemień Krzysztof Szczypiorski Artur Janicki Detection of Image Steganography Using Deep Learning and Ensemble Classifiers Electronics steganography machine learning image processing BOSS database ensemble classifier deep learning |
| title | Detection of Image Steganography Using Deep Learning and Ensemble Classifiers |
| title_full | Detection of Image Steganography Using Deep Learning and Ensemble Classifiers |
| title_fullStr | Detection of Image Steganography Using Deep Learning and Ensemble Classifiers |
| title_full_unstemmed | Detection of Image Steganography Using Deep Learning and Ensemble Classifiers |
| title_short | Detection of Image Steganography Using Deep Learning and Ensemble Classifiers |
| title_sort | detection of image steganography using deep learning and ensemble classifiers |
| topic | steganography machine learning image processing BOSS database ensemble classifier deep learning |
| url | https://www.mdpi.com/2079-9292/11/10/1565 |
| work_keys_str_mv | AT mikołajpłachta detectionofimagesteganographyusingdeeplearningandensembleclassifiers AT marekkrzemien detectionofimagesteganographyusingdeeplearningandensembleclassifiers AT krzysztofszczypiorski detectionofimagesteganographyusingdeeplearningandensembleclassifiers AT arturjanicki detectionofimagesteganographyusingdeeplearningandensembleclassifiers |