Exploring features for membership inference in ASR model auditing
Teixeira, Francisco Pizzi, Karla Olivier, Raphael Abad, Alberto Raj, Bhiksha Trancoso, Isabel
Teixeira, Francisco
Pizzi, Karla
Olivier, Raphael
Abad, Alberto
Raj, Bhiksha
Trancoso, Isabel
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Journal article
Date
2026
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
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. We compare our proposed features with commonly used error-based features for both sample-level and speaker-level MI. We 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 obtain 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. © 2025 Elsevier Ltd
Citation
F. Teixeira, K. Pizzi, R. Olivier, A. Abad, B. Raj, and I. Trancoso, “Exploring features for membership inference in ASR model auditing,” Comput Speech Lang, vol. 95, p. 101812, Jan. 2026, doi: 10.1016/J.CSL.2025.101812.
Source
Computer Speech and Language
Conference
Keywords
Automatic speech recognition, Membership inference, Privacy, Trustworthy machine learning
Subjects
Source
Publisher
Elsevier