Learning to Generate Steganographic Cover for Audio Steganography Using GAN
Audio steganography aims to exploit the human auditory redundancy to embed the secret message into cover audio, without raising suspicion when hearing it. However, recent studies have shown that the existing audio steganography can be easily exposed with the deep learning based steganalyzers by extr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9459771/ |
| _version_ | 1818848348574056448 |
|---|---|
| author | Lang Chen Rangding Wang Diqun Yan Jie Wang |
| author_facet | Lang Chen Rangding Wang Diqun Yan Jie Wang |
| author_sort | Lang Chen |
| collection | DOAJ |
| description | Audio steganography aims to exploit the human auditory redundancy to embed the secret message into cover audio, without raising suspicion when hearing it. However, recent studies have shown that the existing audio steganography can be easily exposed with the deep learning based steganalyzers by extracting high-dimensional features of stego audio for classification. The existing GAN-based steganography approaches mainly studied in images cover, less work is conducted on audio cover. In addition, though a few GAN-based audio steganography methods have been proposed, they still have room for improvements in perceptual quality and undetectability. In this work, we propose an audio steganography framework that could automatically learn to generate superior steganographic cover audio for message embedding. Specifically, the training framework of the proposed framework consists of three components, namely, generator, discriminator and trained deep learning based steganalyzer. Then the traditional message embedding algorithm LSBM, is employed to embed the secret message into the steganographic cover audio to obtain stego audio, which is delivered to the trained steganalyzer for misclassifying as cover audio. Once the adversarial training is completed among these three parties, one can obtain a well-trained generator, which could generate steganographic cover audio for subsequent message embedding. In the practice of our proposed method, the stego audio is produced by embedding the secret message into the steganographic cover audio using a traditional steganography method. Experimental results demonstrate that our proposed audio steganography can yield steganographic cover audio that preserves a quite high perception quality for message embedding. We have compared the detection accuracies with the existing audio steganography schemes as presented in our experiment, the proposed method exhibits lower detection accuracies against the state-of-the-art deep learning based steganalyzers, under various embedding rates. Codes are publicly available at <uri>https://github.com/Chenlang2018/Audio-Steganography-using-GAN</uri>. |
| first_indexed | 2024-12-19T06:15:55Z |
| format | Article |
| id | doaj.art-5294cec187614804af84b482c23e771a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T06:15:55Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5294cec187614804af84b482c23e771a2022-12-21T20:32:51ZengIEEEIEEE Access2169-35362021-01-019880988810710.1109/ACCESS.2021.30904459459771Learning to Generate Steganographic Cover for Audio Steganography Using GANLang Chen0https://orcid.org/0000-0003-2493-8717Rangding Wang1https://orcid.org/0000-0003-2576-8705Diqun Yan2https://orcid.org/0000-0002-5241-7276Jie Wang3https://orcid.org/0000-0002-2748-9884Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaAudio steganography aims to exploit the human auditory redundancy to embed the secret message into cover audio, without raising suspicion when hearing it. However, recent studies have shown that the existing audio steganography can be easily exposed with the deep learning based steganalyzers by extracting high-dimensional features of stego audio for classification. The existing GAN-based steganography approaches mainly studied in images cover, less work is conducted on audio cover. In addition, though a few GAN-based audio steganography methods have been proposed, they still have room for improvements in perceptual quality and undetectability. In this work, we propose an audio steganography framework that could automatically learn to generate superior steganographic cover audio for message embedding. Specifically, the training framework of the proposed framework consists of three components, namely, generator, discriminator and trained deep learning based steganalyzer. Then the traditional message embedding algorithm LSBM, is employed to embed the secret message into the steganographic cover audio to obtain stego audio, which is delivered to the trained steganalyzer for misclassifying as cover audio. Once the adversarial training is completed among these three parties, one can obtain a well-trained generator, which could generate steganographic cover audio for subsequent message embedding. In the practice of our proposed method, the stego audio is produced by embedding the secret message into the steganographic cover audio using a traditional steganography method. Experimental results demonstrate that our proposed audio steganography can yield steganographic cover audio that preserves a quite high perception quality for message embedding. We have compared the detection accuracies with the existing audio steganography schemes as presented in our experiment, the proposed method exhibits lower detection accuracies against the state-of-the-art deep learning based steganalyzers, under various embedding rates. Codes are publicly available at <uri>https://github.com/Chenlang2018/Audio-Steganography-using-GAN</uri>.https://ieeexplore.ieee.org/document/9459771/Audio steganographydeep learning based steganalysisgenerative adversarial network (GAN) |
| spellingShingle | Lang Chen Rangding Wang Diqun Yan Jie Wang Learning to Generate Steganographic Cover for Audio Steganography Using GAN IEEE Access Audio steganography deep learning based steganalysis generative adversarial network (GAN) |
| title | Learning to Generate Steganographic Cover for Audio Steganography Using GAN |
| title_full | Learning to Generate Steganographic Cover for Audio Steganography Using GAN |
| title_fullStr | Learning to Generate Steganographic Cover for Audio Steganography Using GAN |
| title_full_unstemmed | Learning to Generate Steganographic Cover for Audio Steganography Using GAN |
| title_short | Learning to Generate Steganographic Cover for Audio Steganography Using GAN |
| title_sort | learning to generate steganographic cover for audio steganography using gan |
| topic | Audio steganography deep learning based steganalysis generative adversarial network (GAN) |
| url | https://ieeexplore.ieee.org/document/9459771/ |
| work_keys_str_mv | AT langchen learningtogeneratesteganographiccoverforaudiosteganographyusinggan AT rangdingwang learningtogeneratesteganographiccoverforaudiosteganographyusinggan AT diqunyan learningtogeneratesteganographiccoverforaudiosteganographyusinggan AT jiewang learningtogeneratesteganographiccoverforaudiosteganographyusinggan |