# A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations

arXiv: https://arxiv.org/abs/2506.03425 · HTML: https://mlsanity.com/paper/2506.03425/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers](https://mlsanity.com/paper/2402.05602/) (2024)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing](https://mlsanity.com/paper/2111.04433/) (2021)
- [Common Sense Reasoning for Deepfake Detection](https://mlsanity.com/paper/2402.00126/) (2024)
- [FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion](https://mlsanity.com/paper/2406.08603/) (2024)
- [Neural source-filter waveform models for statistical parametric speech synthesis](https://mlsanity.com/paper/1904.12088/) (2019)
- [AI-Synthesized Voice Detection Using Neural Vocoder Artifacts](https://mlsanity.com/paper/2304.13085/) (2023)
- [DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion](https://mlsanity.com/paper/2410.04372/) (2024)
- [A Survey on Speech Deepfake Detection](https://mlsanity.com/paper/2404.13914/) (2024)
- [Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders](https://mlsanity.com/paper/2210.10570/) (2022)
- [Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?](https://mlsanity.com/paper/2309.06014/) (2023)
- [An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verification](https://mlsanity.com/paper/2004.06422/) (2020)
- [Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations](https://mlsanity.com/paper/2110.03309/) (2021)
- [Listenable Maps for Audio Classifiers](https://mlsanity.com/paper/2403.13086/) (2024)
- [How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?](https://mlsanity.com/paper/2406.02483/) (2024)
- [Explainable deepfake and spoofing detection: an attack analysis using SHapley Additive exPlanations](https://mlsanity.com/paper/2202.13693/) (2022)
- [Diffusion-Based Adversarial Purification for Speaker Verification](https://mlsanity.com/paper/2310.14270/) (2023)
- [Interpretable Temporal Class Activation Representation for Audio Spoofing Detection](https://mlsanity.com/paper/2406.08825/) (2024)
- [LMAC-TD: Producing Time Domain Explanations for Audio Classifiers](https://mlsanity.com/paper/2409.08655/) (2024)
- [What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain](https://mlsanity.com/paper/2501.13887/) (2025)
- [Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.08320/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions](https://mlsanity.com/paper/2606.14466/) (2026)
- [Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection](https://mlsanity.com/paper/2607.26472/) (2026)

## Abstract (arXiv)

Evaluating explainability techniques, such as SHAP and LRP, in the context of audio deepfake detection is challenging due to lack of clear ground truth annotations. In the cases when we are able to obtain the ground truth, we find that these methods struggle to provide accurate explanations. In this work, we propose a novel data-driven approach to identify artifact regions in deepfake audio. We consider paired real and vocoded audio, and use the difference in time-frequency representation as the ground-truth explanation. The difference signal then serves as a supervision to train a diffusion model to expose the deepfake artifacts in a given vocoded audio. Experimental results on the VocV4 and LibriSeVoc datasets demonstrate that our method outperforms traditional explainability techniques, both qualitatively and quantitatively.