Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.13464 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914265463521280 |
|---|---|
| author | Gao, Chongyang Postiglione, Marco Baldwin, Julian Denisenko, Natalia Gortner, Isabel Fosdick, Luke Pulice, Chiara Kraus, Sarit Subrahmanian, V. S. |
| author_facet | Gao, Chongyang Postiglione, Marco Baldwin, Julian Denisenko, Natalia Gortner, Isabel Fosdick, Luke Pulice, Chiara Kraus, Sarit Subrahmanian, V. S. |
| contents | Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset (JDD) of 255 public deepfakes which were primarily contributed by over 70 journalists since early 2024. We also generate a synthetic audio dataset (SYN) of dead public figures and propose a novel Context-based Audio Deepfake Detector (CADD) architecture. In addition, we evaluate performance on two large-scale datasets: ITW and P$^2$V. We show that sufficient context and/or the transcript can significantly improve the efficacy of audio deepfake detectors. Performance (measured via F1 score, AUC, and EER) of multiple baseline audio deepfake detectors and traditional classifiers can be improved by 5%-37.58% in F1-score, 3.77%-42.79% in AUC, and 6.17%-47.83% in EER. We additionally show that CADD, via its use of context and/or transcripts, is more robust to 5 adversarial evasion strategies, limiting performance degradation to an average of just -0.71% across all experiments. Code, models, and datasets are available at our project page: https://sites.northwestern.edu/nsail/cadd-context-based-audio-deepfake-detection (access restricted during review). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13464 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Context and Transcripts Improve Detection of Deepfake Audios of Public Figures Gao, Chongyang Postiglione, Marco Baldwin, Julian Denisenko, Natalia Gortner, Isabel Fosdick, Luke Pulice, Chiara Kraus, Sarit Subrahmanian, V. S. Artificial Intelligence Sound Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset (JDD) of 255 public deepfakes which were primarily contributed by over 70 journalists since early 2024. We also generate a synthetic audio dataset (SYN) of dead public figures and propose a novel Context-based Audio Deepfake Detector (CADD) architecture. In addition, we evaluate performance on two large-scale datasets: ITW and P$^2$V. We show that sufficient context and/or the transcript can significantly improve the efficacy of audio deepfake detectors. Performance (measured via F1 score, AUC, and EER) of multiple baseline audio deepfake detectors and traditional classifiers can be improved by 5%-37.58% in F1-score, 3.77%-42.79% in AUC, and 6.17%-47.83% in EER. We additionally show that CADD, via its use of context and/or transcripts, is more robust to 5 adversarial evasion strategies, limiting performance degradation to an average of just -0.71% across all experiments. Code, models, and datasets are available at our project page: https://sites.northwestern.edu/nsail/cadd-context-based-audio-deepfake-detection (access restricted during review). |
| title | Context and Transcripts Improve Detection of Deepfake Audios of Public Figures |
| topic | Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2601.13464 |