# Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation

arXiv: https://arxiv.org/abs/2501.14240 · HTML: https://mlsanity.com/paper/2501.14240/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2025.

## Built on by (most cited first, 8 of 8)

- [Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing](https://mlsanity.com/paper/2504.05657/) (2025)
- [Multi-level SSL Feature Gating for Audio Deepfake Detection](https://mlsanity.com/paper/2509.03409/) (2025)
- [Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection](https://mlsanity.com/paper/2509.20682/) (2025)
- [Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment](https://mlsanity.com/paper/2509.23618/) (2025)
- [Teffic-Audio: Tell Fact from Fiction](https://mlsanity.com/paper/2607.28351/) (2026)
- [From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection](https://mlsanity.com/paper/2605.27944/) (2026)
- [Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection](https://mlsanity.com/paper/2608.13817/) (2026)
- [Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection](https://mlsanity.com/paper/2609.37586/) (2026)

## Abstract (arXiv)

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a novel strategy that integrates Latent Space Refinement (LSR) and Latent Space Augmentation (LSA) to improve the generalization of deepfake detection systems. LSR introduces multiple learnable prototypes for the spoof class, refining the latent space to better capture the intricate variations within spoofed data. LSA further diversifies spoofed data representations by applying augmentation techniques directly in the latent space, enabling the model to learn a broader range of spoofing patterns. We evaluated our approach on four representative datasets, i.e. ASVspoof 2019 LA, ASVspoof 2021 LA and DF, and In-The-Wild. The results show that LSR and LSA perform well individually, and their integration achieves competitive results, matching or surpassing current state-of-the-art methods.