Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes
Detecting audio deepfakes is crucial to ensure authenticity and security, especially in contexts where audio veracity can have critical implications, such as in the legal, security or human rights domains. Various elements, such as complex acoustic backgrounds, enhance the realism of deepfakes; howe...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589284989730816 |
|---|---|
| author | Alba Martínez-Serrano Claudia Montero-Ramírez Carmen Peláez-Moreno |
| author_facet | Alba Martínez-Serrano Claudia Montero-Ramírez Carmen Peláez-Moreno |
| author_sort | Alba Martínez-Serrano |
| collection | DOAJ |
| description | Detecting audio deepfakes is crucial to ensure authenticity and security, especially in contexts where audio veracity can have critical implications, such as in the legal, security or human rights domains. Various elements, such as complex acoustic backgrounds, enhance the realism of deepfakes; however, their effect on the processes of creation and detection of deepfakes remains under-explored. This study systematically analyses how factors such as the acoustic environment, user type and signal-to-noise ratio influence the quality and detectability of deepfakes. For this study, we use the <i>WELIVE</i> dataset, which contains audio recordings of 14 female victims of gender-based violence in real and uncontrolled environments. The results indicate that the complexity of the acoustic scene affects both the generation and detection of deepfakes: classifiers, particularly the linear SVM, are more effective in complex acoustic environments, suggesting that simpler acoustic environments may facilitate the generation of more realistic deepfakes and, in turn, make it more difficult for classifiers to detect them. These findings underscore the need to develop adaptive models capable of handling diverse acoustic environments, thus improving detection reliability in dynamic and real-world contexts. |
| format | Article |
| id | doaj-art-b2b0c19671f64fd4906401abe473d491 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-b2b0c19671f64fd4906401abe473d4912025-01-24T13:19:49ZengMDPI AGApplied Sciences2076-34172025-01-0115255810.3390/app15020558Authenticity at Risk: Key Factors in the Generation and Detection of Audio DeepfakesAlba Martínez-Serrano0Claudia Montero-Ramírez1Carmen Peláez-Moreno2Signal Theory and Communications Department, University Carlos III of Madrid, 28911 Madrid, SpainSignal Theory and Communications Department, University Carlos III of Madrid, 28911 Madrid, SpainSignal Theory and Communications Department, University Carlos III of Madrid, 28911 Madrid, SpainDetecting audio deepfakes is crucial to ensure authenticity and security, especially in contexts where audio veracity can have critical implications, such as in the legal, security or human rights domains. Various elements, such as complex acoustic backgrounds, enhance the realism of deepfakes; however, their effect on the processes of creation and detection of deepfakes remains under-explored. This study systematically analyses how factors such as the acoustic environment, user type and signal-to-noise ratio influence the quality and detectability of deepfakes. For this study, we use the <i>WELIVE</i> dataset, which contains audio recordings of 14 female victims of gender-based violence in real and uncontrolled environments. The results indicate that the complexity of the acoustic scene affects both the generation and detection of deepfakes: classifiers, particularly the linear SVM, are more effective in complex acoustic environments, suggesting that simpler acoustic environments may facilitate the generation of more realistic deepfakes and, in turn, make it more difficult for classifiers to detect them. These findings underscore the need to develop adaptive models capable of handling diverse acoustic environments, thus improving detection reliability in dynamic and real-world contexts.https://www.mdpi.com/2076-3417/15/2/558audio deepfakegenerationdetectionacoustic context |
| spellingShingle | Alba Martínez-Serrano Claudia Montero-Ramírez Carmen Peláez-Moreno Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes Applied Sciences audio deepfake generation detection acoustic context |
| title | Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes |
| title_full | Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes |
| title_fullStr | Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes |
| title_full_unstemmed | Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes |
| title_short | Authenticity at Risk: Key Factors in the Generation and Detection of Audio Deepfakes |
| title_sort | authenticity at risk key factors in the generation and detection of audio deepfakes |
| topic | audio deepfake generation detection acoustic context |
| url | https://www.mdpi.com/2076-3417/15/2/558 |
| work_keys_str_mv | AT albamartinezserrano authenticityatriskkeyfactorsinthegenerationanddetectionofaudiodeepfakes AT claudiamonteroramirez authenticityatriskkeyfactorsinthegenerationanddetectionofaudiodeepfakes AT carmenpelaezmoreno authenticityatriskkeyfactorsinthegenerationanddetectionofaudiodeepfakes |