The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio

TL;DR

This paper introduces the Codecfake dataset and a novel countermeasure, CSAM, to improve the universal detection of ALM-based deepfake audio, demonstrating significant reduction in error rates across diverse test conditions.

Contribution

The paper presents the large-scale Codecfake dataset and a domain-balanced CSAM strategy to enhance generalization in deepfake audio detection.

Findings

Effective detection of ALM-based deepfake audio using the dataset.

CSAM achieves the lowest EER of 0.616% across test conditions.

Dataset and code are publicly available.

Abstract

With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods. ALM-based deepfake audio currently exhibits widespread, high deception, and type versatility, posing a significant challenge to current audio deepfake detection (ADD) models trained solely on vocoded data. To effectively detect ALM-based deepfake audio, we focus on the mechanism of the ALM-based audio generation method, the conversion from neural codec to waveform. We initially constructed the Codecfake dataset, an open-source, large-scale collection comprising over 1 million audio samples in both English and Chinese, focus on ALM-based audio detection. As countermeasure, to achieve universal detection of deepfake audio and tackle domain ascent bias issue of original sharpness aware minimization (SAM), we propose the CSAM strategy to learn a domain balanced and generalized minima. In our experiments, we first demonstrate that ADD model training with the Codecfake dataset can effectively detects ALM-based audio. Furthermore, our proposed generalization countermeasure yields the lowest average equal error rate (EER) of 0.616% across all test conditions compared to baseline models. The dataset and associated code are available online.