What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Face SwappingSensitivitytext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Interpreting Verbal Irony: Linguistic Strategies and the Connection to the Type of Semantic Incongruity
Human communication often involves the use of verbal irony or sarcasm, where the speakers usually mean the opposite of what they say. To better understand how verbal irony is expressed by the speaker and interpreted by t…
How to Engage Your Readers? Generating Guiding Questions to Promote Active Reading
Using questions in written text is an effective strategy to enhance readability. However, what makes an active reading question good, what the linguistic role of these questions is, and what is their impact on human read…
ArticlesMemorizationReading ComprehensionWhat BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models
Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper…
Language ModelingLanguage ModellingNegationHarnessing the linguistic signal to predict scalar inferences
Pragmatic inferences often subtly depend on the presence or absence of linguistic features. For example, the presence of a partitive construction (of the) increases the strength of a so-called scalar inference: listeners…
SentenceThe Fewer Splits are Better: Deconstructing Readability in Sentence Splitting
In this work, we focus on sentence splitting, a subfield of text simplification, motivated largely by an unproven idea that if you divide a sentence in pieces, it should become easier to understand. Our primary goal in t…
SentenceText Simplification