# Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption

arXiv: https://arxiv.org/abs/2503.17577 · HTML: https://mlsanity.com/paper/2503.17577/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec](https://mlsanity.com/paper/2305.16608/) (2023)
- [Investigating self-supervised front ends for speech spoofing countermeasures](https://mlsanity.com/paper/2111.07725/) (2021)
- [Improved DeepFake Detection Using Whisper Features](https://mlsanity.com/paper/2306.01428/) (2023)
- [Voices Obscured in Complex Environmental Settings (VOICES) corpus](https://mlsanity.com/paper/1804.05053/) (2018)
- [AudioMarkBench: Benchmarking Robustness of Audio Watermarking](https://mlsanity.com/paper/2406.06979/) (2024)
- [Cross-Domain Audio Deepfake Detection: Dataset and Analysis](https://mlsanity.com/paper/2404.04904/) (2024)

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

- [Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio Attribution](https://mlsanity.com/paper/2609.07981/) (2026)
- [Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection](https://mlsanity.com/paper/2609.20063/) (2026)

## Abstract (arXiv)

Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos. Among these, audio deepfakes are particularly alarming due to the growing accessibility of high-quality voice synthesis tools and the ease with which synthetic speech can be distributed through social media and robocalls. Consequently, detecting audio deepfakes is critical for combating the misuse of AI-generated speech. However, real-world audio is often affected by corruptions such as noise, audio modification, and compression, which can significantly degrade detection performance. In this work, we systematically evaluate the robustness of 10 audio deepfake detection models against 18 common corruption types, grouped into three categories: noise perturbation, audio modification, and compression. Using both traditional deep learning models and state-of-the-art speech foundation models, our study yields four key insights. (1) Most models are robust to noise but remain vulnerable to audio modifications and compression, especially neural codecs. (2) Speech foundation models consistently outperform traditional models across most corruption scenarios, likely due to large-scale pre-training on diverse audio datasets. (3) Increasing model size improves robustness, although the gains diminish as models become larger. (4) Robustness to unseen corruptions can be improved through targeted data augmentation during training or speech enhancement at inference time. These findings highlight the importance of evaluating audio deepfake detectors under diverse real-world corruptions and developing more robust detection frameworks for practical deployment. We further advocate that future research on deepfake detection across all media should account for the diverse and unpredictable distortions encountered in real-world environments.