Cross-Domain Audio Deepfake Detection: Dataset and Analysis
- URL: http://arxiv.org/abs/2404.04904v1
- Date: Sun, 7 Apr 2024 10:10:15 GMT
- Title: Cross-Domain Audio Deepfake Detection: Dataset and Analysis
- Authors: Yuang Li, Min Zhang, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Hao Yang,
- Abstract summary: Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy.
Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance.
We construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models.
- Score: 11.985093463886056
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models. To simulate real-world scenarios, we employ diverse attack methods and audio prompts from different datasets. Experiments show that, through novel attack-augmented training, the Wav2Vec2-large and Whisper-medium models achieve equal error rates of 4.1\% and 6.5\% respectively. Additionally, we demonstrate our models' outstanding few-shot ADD ability by fine-tuning with just one minute of target-domain data. Nonetheless, neural codec compressors greatly affect the detection accuracy, necessitating further research.
Related papers
- The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio [42.84634652376024]
ALM-based deepfake audio exhibits widespread, high deception, and type versatility.
To effectively detect ALM-based deepfake audio, we focus on the mechanism of the ALM-based audio generation method.
We propose the CSAM strategy to learn a domain balanced and generalized minima.
arXiv Detail & Related papers (2024-05-08T08:28:40Z) - Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models [52.04189118767758]
Generalization is a main issue for current audio deepfake detectors.
In this paper we study the potential of large-scale pre-trained models for audio deepfake detection.
arXiv Detail & Related papers (2024-05-03T15:27:11Z) - An RFP dataset for Real, Fake, and Partially fake audio detection [0.36832029288386137]
The paper presents the RFP da-taset, which comprises five distinct audio types: partial fake (PF), audio with noise, voice conversion (VC), text-to-speech (TTS), and real.
The data are then used to evaluate several detection models, revealing that the available models incur a markedly higher equal error rate (EER) when detecting PF audio instead of entirely fake audio.
arXiv Detail & Related papers (2024-04-26T23:00:56Z) - SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised
Learning for Robust Infrared Small Target Detection [53.19618419772467]
Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds.
With the development of Transformer, the scale of SIRST models is constantly increasing.
With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
arXiv Detail & Related papers (2024-03-08T16:14:54Z) - Deepfake audio as a data augmentation technique for training automatic
speech to text transcription models [55.2480439325792]
We propose a framework that approaches data augmentation based on deepfake audio.
A dataset produced by Indians (in English) was selected, ensuring the presence of a single accent.
arXiv Detail & Related papers (2023-09-22T11:33:03Z) - Improved DeepFake Detection Using Whisper Features [2.846767128062884]
We investigate the influence of Whisper automatic speech recognition model as a DF detection front-end.
We show that using Whisper-based features improves the detection for each model and outperforms recent results on the In-The-Wild dataset by reducing Equal Error Rate by 21%.
arXiv Detail & Related papers (2023-06-02T10:34:05Z) - DAD: Data-free Adversarial Defense at Test Time [21.741026088202126]
Deep models are highly susceptible to adversarial attacks.
Privacy has become an important concern, restricting access to only trained models but not the training data.
We propose a completely novel problem of 'test-time adversarial defense in absence of training data and even their statistics'
arXiv Detail & Related papers (2022-04-04T15:16:13Z) - Device-Directed Speech Detection: Regularization via Distillation for
Weakly-Supervised Models [13.456066434598155]
We address the problem of detecting speech directed to a device that does not contain a specific wake-word.
Specifically, we focus on audio coming from a touch-based invocation.
arXiv Detail & Related papers (2022-03-30T01:27:39Z) - Continual Learning for Fake Audio Detection [62.54860236190694]
This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally.
Experiments are conducted on the ASVspoof 2019 dataset.
arXiv Detail & Related papers (2021-04-15T07:57:05Z) - Detection in Crowded Scenes: One Proposal, Multiple Predictions [79.28850977968833]
We propose a proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.
The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks.
Our detector can obtain 4.9% AP gains on challenging CrowdHuman dataset and 1.0% $textMR-2$ improvements on CityPersons dataset.
arXiv Detail & Related papers (2020-03-20T09:48:53Z) - Stance Detection Benchmark: How Robust Is Your Stance Detection? [65.91772010586605]
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim.
We introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning setting.
Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets.
arXiv Detail & Related papers (2020-01-06T13:37:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.