Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
This work addresses privacy threats and auditing needs for ASR systems, but it is incremental as it builds on existing error-based features.
The paper tackled membership inference in automatic speech recognition models by using loss-based features with perturbations, finding that these features greatly enhance sample-level performance and improve speaker-level results, though less significantly.
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 features and find that the proposed features greatly enhance performance for sample-level MI. For speaker-level MI, these features improve results, though by a smaller margin, as error-based features already obtained a high performance for this task. Our findings emphasise the importance of considering different feature sets and levels of access to target models for effective MI in ASR systems, providing valuable insights for auditing such models.