Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography
This paper presents an extensive investigation into the application of artificial intelligence, specifically Convolutional Neural Networks (CNNs), in image steganography detection. We initially evaluated the state-of-the-art steganalysis model, SRNet, on various image steganography techniques, inclu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/23/7815 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849220405651308544 |
|---|---|
| author | Oleksandr Kuznetsov Emanuele Frontoni Kyrylo Chernov Kateryna Kuznetsova Ruslan Shevchuk Mikolaj Karpinski |
| author_facet | Oleksandr Kuznetsov Emanuele Frontoni Kyrylo Chernov Kateryna Kuznetsova Ruslan Shevchuk Mikolaj Karpinski |
| author_sort | Oleksandr Kuznetsov |
| collection | DOAJ |
| description | This paper presents an extensive investigation into the application of artificial intelligence, specifically Convolutional Neural Networks (CNNs), in image steganography detection. We initially evaluated the state-of-the-art steganalysis model, SRNet, on various image steganography techniques, including WOW, HILL, S-UNIWARD, and the innovative Spread Spectrum Image Steganography (SSIS). We found SRNet’s performance on SSIS detection to be lower compared to other methods, prompting us to fine-tune the model using SSIS datasets. Subsequent experiments showed significant improvement in SSIS detection, albeit at the cost of minor performance degradation as to other techniques. Our findings underscore the potential and adaptability of AI-based steganalysis models. However, they also highlight the need for a delicate balance in model adaptation to maintain effectiveness across various steganography techniques. We suggest future research directions, including multi-task learning strategies and other machine learning techniques, to further improve the robustness and versatility of steganalysis models. |
| format | Article |
| id | doaj-art-db9d1eae3d3f4449b359e599490fb5c4 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-db9d1eae3d3f4449b359e599490fb5c42024-12-13T16:32:52ZengMDPI AGSensors1424-82202024-12-012423781510.3390/s24237815Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image SteganographyOleksandr Kuznetsov0Emanuele Frontoni1Kyrylo Chernov2Kateryna Kuznetsova3Ruslan Shevchuk4Mikolaj Karpinski5Department of Theoretical and Applied Sciences, eCampus University, Via Isimbardi 10, 22060 Novedrate, ItalyDepartment of Political Sciences, Communication and International Relations, University of Macerata, Via Crescimbeni, 30/32, 62100 Macerata, ItalyDepartment of Information and Communication Systems Security, School of Computer Sciences, V. N. Karazin Kharkiv National University, 4 Svobody Sq., 61022 Kharkiv, UkraineVRAI—Vision, Robotics and Artificial Intelligence Lab, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Computer Science and Automatics, University of Bielsko-Biala, 43-309 Bielsko-Biala, PolandInstitute of Security and Computer Science, University of the National Education Commission, 30-084 Krakow, PolandThis paper presents an extensive investigation into the application of artificial intelligence, specifically Convolutional Neural Networks (CNNs), in image steganography detection. We initially evaluated the state-of-the-art steganalysis model, SRNet, on various image steganography techniques, including WOW, HILL, S-UNIWARD, and the innovative Spread Spectrum Image Steganography (SSIS). We found SRNet’s performance on SSIS detection to be lower compared to other methods, prompting us to fine-tune the model using SSIS datasets. Subsequent experiments showed significant improvement in SSIS detection, albeit at the cost of minor performance degradation as to other techniques. Our findings underscore the potential and adaptability of AI-based steganalysis models. However, they also highlight the need for a delicate balance in model adaptation to maintain effectiveness across various steganography techniques. We suggest future research directions, including multi-task learning strategies and other machine learning techniques, to further improve the robustness and versatility of steganalysis models.https://www.mdpi.com/1424-8220/24/23/7815image steganography detectionconvolutional neural networksfine-tuningspread spectrum image steganographysteganalysis models |
| spellingShingle | Oleksandr Kuznetsov Emanuele Frontoni Kyrylo Chernov Kateryna Kuznetsova Ruslan Shevchuk Mikolaj Karpinski Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography Sensors image steganography detection convolutional neural networks fine-tuning spread spectrum image steganography steganalysis models |
| title | Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography |
| title_full | Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography |
| title_fullStr | Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography |
| title_full_unstemmed | Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography |
| title_short | Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography |
| title_sort | enhancing steganography detection with ai fine tuning a deep residual network for spread spectrum image steganography |
| topic | image steganography detection convolutional neural networks fine-tuning spread spectrum image steganography steganalysis models |
| url | https://www.mdpi.com/1424-8220/24/23/7815 |
| work_keys_str_mv | AT oleksandrkuznetsov enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography AT emanuelefrontoni enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography AT kyrylochernov enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography AT katerynakuznetsova enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography AT ruslanshevchuk enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography AT mikolajkarpinski enhancingsteganographydetectionwithaifinetuningadeepresidualnetworkforspreadspectrumimagesteganography |