Papers
arxiv:2509.21597

AUDDT: Audio Unified Deepfake Detection Benchmark Toolkit

Published on Sep 25
Authors:
,
,
,

Abstract

AUDDT is an open-source benchmarking toolkit for evaluating pretrained audio deepfake detectors across multiple datasets, highlighting their performance and limitations.

AI-generated summary

With the prevalence of artificial intelligence (AI)-generated content, such as audio deepfakes, a large body of recent work has focused on developing deepfake detection techniques. However, most models are evaluated on a narrow set of datasets, leaving their generalization to real-world conditions uncertain. In this paper, we systematically review 28 existing audio deepfake datasets and present an open-source benchmarking toolkit called AUDDT (https://github.com/MuSAELab/AUDDT). The goal of this toolkit is to automate the evaluation of pretrained detectors across these 28 datasets, giving users direct feedback on the advantages and shortcomings of their deepfake detectors. We start by showcasing the usage of the developed toolkit, the composition of our benchmark, and the breakdown of different deepfake subgroups. Next, using a widely adopted pretrained deepfake detector, we present in- and out-of-domain detection results, revealing notable differences across conditions and audio manipulation types. Lastly, we also analyze the limitations of these existing datasets and their gap relative to practical deployment scenarios.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.21597 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.21597 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.21597 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.