Anti-Forensics of Audio Source Identification Using Generative Adversarial Network
Digital audio recording is the main evidence used in the field of judicial forensics. Recently, a number of digital audio forensic techniques have been developed and the audio source identification (ASI) is one of the most active research topics. Most of existing ASI works mainly focus on improving...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8933418/ |
| _version_ | 1818855285617328128 |
|---|---|
| author | Xiaowen Li Diqun Yan Li Dong Rangding Wang |
| author_facet | Xiaowen Li Diqun Yan Li Dong Rangding Wang |
| author_sort | Xiaowen Li |
| collection | DOAJ |
| description | Digital audio recording is the main evidence used in the field of judicial forensics. Recently, a number of digital audio forensic techniques have been developed and the audio source identification (ASI) is one of the most active research topics. Most of existing ASI works mainly focus on improving the performance of detection accuracy and robustness. Little consideration has been given to ASI anti-forensics, which aims at attacking the forensic techniques. To expose the weaknesses of these source identification methods, we propose an anti-forensic framework based on generative adversarial network (GAN) to falsify the source information of an audio by adding specific disturbance. The experimental results show that the falsified audio can deceive the forensic methods effectively, and can even control their conclusions. Three state-of-art ASI methods have been evaluated as the attacking targets. For the confusing attack, the proposed method can significantly reduce their detection accuracies from about 97% to less than 5%. For the misleading attack, a misleading rate about 81.32% has been achieved while ensuring the perceptual quality of the anti-forensic audio. |
| first_indexed | 2024-12-19T08:06:11Z |
| format | Article |
| id | doaj.art-ede0ea633d2148f19fd1561da065a802 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T08:06:11Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ede0ea633d2148f19fd1561da065a8022022-12-21T20:29:45ZengIEEEIEEE Access2169-35362019-01-01718433218433910.1109/ACCESS.2019.29600978933418Anti-Forensics of Audio Source Identification Using Generative Adversarial NetworkXiaowen Li0https://orcid.org/0000-0002-3058-0347Diqun Yan1https://orcid.org/0000-0002-5241-7276Li Dong2https://orcid.org/0000-0003-2002-8249Rangding Wang3https://orcid.org/0000-0003-2576-8705College of Information Science and Engieering, Ningbo University, Zhejiang, ChinaCollege of Information Science and Engieering, Ningbo University, Zhejiang, ChinaCollege of Information Science and Engieering, Ningbo University, Zhejiang, ChinaCollege of Information Science and Engieering, Ningbo University, Zhejiang, ChinaDigital audio recording is the main evidence used in the field of judicial forensics. Recently, a number of digital audio forensic techniques have been developed and the audio source identification (ASI) is one of the most active research topics. Most of existing ASI works mainly focus on improving the performance of detection accuracy and robustness. Little consideration has been given to ASI anti-forensics, which aims at attacking the forensic techniques. To expose the weaknesses of these source identification methods, we propose an anti-forensic framework based on generative adversarial network (GAN) to falsify the source information of an audio by adding specific disturbance. The experimental results show that the falsified audio can deceive the forensic methods effectively, and can even control their conclusions. Three state-of-art ASI methods have been evaluated as the attacking targets. For the confusing attack, the proposed method can significantly reduce their detection accuracies from about 97% to less than 5%. For the misleading attack, a misleading rate about 81.32% has been achieved while ensuring the perceptual quality of the anti-forensic audio.https://ieeexplore.ieee.org/document/8933418/Generative adversarial networkanti-forensicsaudio source identification |
| spellingShingle | Xiaowen Li Diqun Yan Li Dong Rangding Wang Anti-Forensics of Audio Source Identification Using Generative Adversarial Network IEEE Access Generative adversarial network anti-forensics audio source identification |
| title | Anti-Forensics of Audio Source Identification Using Generative Adversarial Network |
| title_full | Anti-Forensics of Audio Source Identification Using Generative Adversarial Network |
| title_fullStr | Anti-Forensics of Audio Source Identification Using Generative Adversarial Network |
| title_full_unstemmed | Anti-Forensics of Audio Source Identification Using Generative Adversarial Network |
| title_short | Anti-Forensics of Audio Source Identification Using Generative Adversarial Network |
| title_sort | anti forensics of audio source identification using generative adversarial network |
| topic | Generative adversarial network anti-forensics audio source identification |
| url | https://ieeexplore.ieee.org/document/8933418/ |
| work_keys_str_mv | AT xiaowenli antiforensicsofaudiosourceidentificationusinggenerativeadversarialnetwork AT diqunyan antiforensicsofaudiosourceidentificationusinggenerativeadversarialnetwork AT lidong antiforensicsofaudiosourceidentificationusinggenerativeadversarialnetwork AT rangdingwang antiforensicsofaudiosourceidentificationusinggenerativeadversarialnetwork |