Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection

Excerpt

arXiv:2610.05264v1 Announce Type: cross Abstract: Advances in speech synthesis have made deepfake speeches increasingly convincing, posing growing threats to security. While self-supervised learning (SSL) based detectors achieve state-of-the-art performance, their computational demands (typically 300M+ parameters) prevent deployment on resource-constrained devices. Existing compression methods, designed mainly for content-centric tasks, struggle to maintain competitive performance when directly