Saved in:
Bibliographic Details
Main Authors: Gao, Chongyang, Postiglione, Marco, Baldwin, Julian, Denisenko, Natalia, Gortner, Isabel, Fosdick, Luke, Pulice, Chiara, Kraus, Sarit, Subrahmanian, V. S.
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