2024/04/02 by Matthew Jagielski, Jagielski, Matthew, Om Thakkar +3 · 1 citation
Computer Science · #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis
paper · pdf · doi:10.48550/arxiv.2404.02052
openalex publication_date 2024/04/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech recognition (ASR) models by requesting a transcript of an utterance which is partially replaced with noise. They show that when a record has been seen at training time, the model will transcribe the noisy record with its memorized sensitive transcript. In our work, we extend these attacks beyond ASR models, to attack pretrained speech encoders. Our method fine-tunes the encoder to produce an ASR model, and then performs noise masking on this model, which we find recovers private information from the pretraining data, despite the model never having seen transcripts at pretraining time! We show how to improve the precision of these attacks and investigate a number of countermeasures to our attacks.