Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
This work addresses domain adaptation challenges in audio deepfake detection, offering a computationally efficient solution for scenarios with limited target data, though it is incremental as it builds on existing prompt tuning techniques.
The paper tackles the problem of audio deepfake detection under domain gaps by proposing a prompt tuning method that integrates with transformer models, achieving enhanced accuracy with minimal target data and low computational cost.
We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt tuning in a plug-in style. It bridges domain gaps by integrating it seamlessly with state-of-the-art transformer models and/or with other fine-tuning methods, boosting their performance on target data (challenge (i)). In addition, our method can fit small target datasets because it does not require a large number of extra parameters (challenge (ii)). This feature also contributes to computational efficiency, countering the high computational costs typically associated with large-scale pre-trained models in ADD (challenge (iii)). We conclude that prompt tuning for ADD under domain gaps presents a promising avenue for enhancing accuracy with minimal target data and negligible extra computational burden.