mlsanityData to 7 Oct 2026

Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features

arXiv 2405.01207 ↗First posted 2 May 2024cs.LG cs.CR cs.SDcited by 2

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 18 of its 28 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

18 of 28 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems14 Sep
  2. 2023An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization26 May
  3. 2022Evaluating Membership Inference Through Adversarial Robustness14 May
  4. 2021Membership Inference Attacks From First Principles7 Dec
  5. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  6. 2021Membership Inference Attacks Against Self-supervised Speech Models9 Nov
  7. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  7. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  8. 2020SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systemscited by 46
  9. 2019The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Servicescited by 25
  10. 2022Recent improvements of ASR models in the face of adversarial attackscited by 13
  11. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Assessing the Effectiveness of Membership Inference on Generative Musiccited by 1
  2. 2026Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Modelscited by 0