mlsanityData to 14 Oct 2026

Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection

arXiv 2509.13878 ↗First posted 17 Sep 2025eess.AS cs.LG cs.SDcited by 2

Not on the map. Why?

Abstract (arXiv)

Foundation models such as Wav2Vec2 excel at representation learning in speech tasks, including audio deepfake detection. However, after being fine-tuned on a fixed set of bonafide and spoofed audio clips, they often fail to generalize to novel deepfake methods not represented in training. To address this, we propose a mixture-of-LoRA-experts approach that integrates multiple low-rank adapters (LoRA) into the model's attention layers. A routing mechanism selectively activates specialized experts, enhancing adaptability to evolving deepfake attacks. Experimental results show that our method outperforms standard fine-tuning in both in-domain and out-of-domain scenarios, reducing equal error rates relative to baseline models. Notably, our best MoE-LoRA model lowers the average out-of-domain EER from 8.55% to 6.08%, demonstrating its effectiveness in achieving generalizable audio deepfake detection.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 17 Sep 2025.

Builds on

25 of 34 references.

References · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  7. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  8. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  9. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  10. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  11. 2022Does Audio Deepfake Detection Generalize?cited by 135
  12. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
13 more
  1. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  2. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 80
  3. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  4. 2021SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Expertscited by 48
  5. 2024AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Expertscited by 34
  6. 2024Leveraging Mixture of Experts for Improved Speech Deepfake Detectioncited by 15
  7. 2020An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verificationcited by 13
  8. 2024Harder or Different? Understanding Generalization of Audio Deepfake Detectioncited by 9
  9. 2023Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detectioncited by 8
  10. 2024Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein modelcited by 6
  11. 2023Adaptive Fake Audio Detection with Low-Rank Model Squeezingcited by 5
  12. 2025Generalizable speech deepfake detection via meta-learned LoRAcited by 4
  13. 2024Meta-Learning Approaches for Improving Detection of Unseen Speech Deepfakescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofingcited by 0
  2. 2026Domain-Adaptive Dual-Gating Mixture of Experts for Generalizable Speech Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detection
  2. 2025Attention-based Mixture of Experts for Robust Speech Deepfake Detection
  3. 2025Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection
  4. 2026Leveraging Gradient Reversal Loss and Multitask Learning for Datasets-Aware Audio Deepfake Detection
  5. 2026Leveraging large multimodal models for audio-video deepfake detection: a pilot study
  6. 2026DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts
  7. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning
  8. 2026SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision