Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features

arXiv:2405.01207v1 Announce Type: cross
Abstract: Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these models with regard to user data. This paper explores the effectiveness of loss-based features in combination with Gaussian and adversarial perturbations to perform MI in ASR models. To the best of our knowledge, this approach has not yet been investigated. We compare our proposed features with commonly used error-based …

arxiv asr audit auditing automatic cs.cr cs.lg cs.sd data eess.as features loss opportunity privacy recognition speech speech recognition systems threat training training data user data