Noise Masking Attacks and Defenses for Pretrained Speech Models

arXiv:2404.02052v1 Announce Type: new
Abstract: 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. …

abstract arxiv asr attacks automatic speech recognition cs.lg data masking noise performance privacy recognition speech speech recognition type work