Continuous Learning of Transformer-based Audio Deepfake Detection

2024/09/09 by Thai‐Ha Le, Le, Tuan Duy Nguyen, Kah Kuan Teh +3 · 1 citation
Computer Science · #Digital Media Forensic Detection #Image and Signal Denoising Methods #Music and Audio Processing

paper · pdf · doi:10.48550/arxiv.2409.05924

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.

Cited by

• Zero-Shot to Zero-Lies: Detecting Bengali Deepfake Audio through Transfer Learning

Related

• What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
• Towards Robust Audio Deepfake Detection: A Evolving Benchmark for Continual Learning
• Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
• Unmasking real-world audio deepfakes: A data-centric approach
• Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Models