# What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection

arXiv: https://arxiv.org/abs/2505.17513 · HTML: https://mlsanity.com/paper/2505.17513/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [ByT5 model for massively multilingual grapheme-to-phoneme conversion](https://mlsanity.com/paper/2204.03067/) (2022)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Defense against adversarial attacks on spoofing countermeasures of ASV](https://mlsanity.com/paper/2003.03065/) (2020)
- [CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning](https://mlsanity.com/paper/2404.15854/) (2024)
- [Meta Learning Text-to-Speech Synthesis in over 7000 Languages](https://mlsanity.com/paper/2406.06403/) (2024)
- [Complex-valued neural networks for voice anti-spoofing](https://mlsanity.com/paper/2308.11800/) (2023)
- [Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection](https://mlsanity.com/paper/2210.17222/) (2022)

## Built on by (most cited first, 1 of 1)

- [Acoustic-based Gender Differentiation in Speech-aware Language Models](https://mlsanity.com/paper/2509.21125/) (2025)

## Abstract (arXiv)

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior work has predominantly focused on acoustic-level perturbations, leaving the impact of linguistic variation largely unexplored. In this paper, we investigate the linguistic sensitivity of both open-source and commercial anti-spoofing detectors by introducing transcript-level adversarial attacks. Our extensive evaluation reveals that even minor linguistic perturbations can significantly degrade detection accuracy: attack success rates surpass 60% on several open-source detector-voice pairs, and notably one commercial detection accuracy drops from 100% on synthetic audio to just 32%. Through a comprehensive feature attribution analysis, we identify that both linguistic complexity and model-level audio embedding similarity contribute strongly to detector vulnerability. We further demonstrate the real-world risk via a case study replicating the Brad Pitt audio deepfake scam, using transcript adversarial attacks to completely bypass commercial detectors. These results highlight the need to move beyond purely acoustic defenses and account for linguistic variation in the design of robust anti-spoofing systems. All source code will be publicly available.