Continuous Learning of Transformer-based Audio Deepfake Detection

TL;DR

This paper introduces a new audio deepfake detection framework using Audio Spectrogram Transformer, emphasizing high accuracy and effective continuous learning with minimal labeled data, demonstrated through extensive dataset collection and augmentation.

Contribution

It presents a novel continuous learning plugin for audio deepfake detection that outperforms traditional fine-tuning with fewer labeled examples.

Findings

Achieved high accuracy on multiple benchmark datasets.

Developed a continuous learning plugin that requires minimal labeled data.

Enhanced detection robustness through diverse data augmentation.

Abstract

This paper proposes a novel framework for audio deepfake detection with two main objectives: i) attaining the highest possible accuracy on available fake data, and ii) effectively performing continuous learning on new fake data in a few-shot learning manner. Specifically, we conduct a large audio deepfake collection using various deep audio generation methods. The data is further enhanced with additional augmentation methods to increase variations amidst compressions, far-field recordings, noise, and other distortions. We then adopt the Audio Spectrogram Transformer for the audio deepfake detection model. Accordingly, the proposed method achieves promising performance on various benchmark datasets. Furthermore, we present a continuous learning plugin module to update the trained model most effectively with the fewest possible labeled data points of the new fake type. The proposed method outperforms the conventional direct fine-tuning approach with much fewer labeled data points.