Privacy attacks for automatic speech recognition acoustic models in a
federated learning framework

v1v2 (latest)

Privacy attacks for automatic speech recognition acoustic models in a federated learning framework

6 November 2021

Salima Mdhaffar

ArXiv (abs)PDF HTML

Papers citing "Privacy attacks for automatic speech recognition acoustic models in a federated learning framework"

18 / 18 papers shown

Title
Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition Salima Mdhaffar J. Bonastre Marc Tommasi N. Tomashenko Yannick Esteve 48 12 0 07 Nov 2021
Federated Learning in ASR: Not as Easy as You Think Wentao Yu J. Freiwald Soren Tewes F. Huennemeyer D. Kolossa FedML 73 17 0 30 Sep 2021
The VoicePrivacy 2020 Challenge: Results and findings N. Tomashenko Xin Wang Emmanuel Vincent J. Patino B. M. L. Srivastava ... Benjamin O’Brien Anais Chanclu J. Bonastre Massimiliano Todisco Mohamed Maouche 113 109 0 01 Sep 2021
Federated Acoustic Modeling For Automatic Speech Recognition Xiaodong Cui Songtao Lu Brian Kingsbury 48 33 0 08 Feb 2021
Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework Dhruv Guliani F. Beaufays Giovanni Motta FedML 37 82 0 29 Oct 2020
Improving on-device speaker verification using federated learning with privacy Filip Granqvist M. Seigel Rogier van Dalen Áine Cahill Stephen Shum Matthias Paulik FedML 49 56 0 06 Aug 2020
Federated Transfer Learning with Dynamic Gradient Aggregation Dimitrios Dimitriadis K. Kumatani R. Gmyr Yashesh Gaur Sefik Emre Eskimez FedML 88 15 0 06 Aug 2020
Training Keyword Spotting Models on Non-IID Data with Federated Learning Andrew Straiton Hard Kurt Partridge Cameron Nguyen Niranjan A. Subrahmanya Aishanee Shah Pai Zhu Ignacio López Moreno Rajiv Mathews OOD FedML 59 67 0 21 May 2020
Introducing the VoicePrivacy Initiative N. Tomashenko B. M. L. Srivastava Xin Wang Emmanuel Vincent A. Nautsch ... Nicholas W. D. Evans J. Patino J. Bonastre Paul-Gauthier Noé Massimiliano Todisco 78 132 0 04 May 2020
Inverting Gradients -- How easy is it to break privacy in federated learning? Jonas Geiping Hartmut Bauermeister Hannah Dröge Michael Moeller FedML 109 1,235 0 31 Mar 2020
Federated Learning: Challenges, Methods, and Future Directions Tian Li Anit Kumar Sahu Ameet Talwalkar Virginia Smith FedML 129 4,540 0 21 Aug 2019
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning Peng Kuang Mengkai Song Zhifei Zhang Yang Song Qian Wang Hairong Qi FedML 84 786 0 03 Dec 2018
Federated Learning for Keyword Spotting David Leroy A. Coucke Thibaut Lavril Thibault Gisselbrecht Joseph Dureau FedML 86 287 0 09 Oct 2018
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation François Hernandez Vincent Nguyen Sahar Ghannay N. Tomashenko Yannick Esteve VLM 76 352 0 12 May 2018
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks Nicholas Carlini Chang-rui Liu Ulfar Erlingsson Jernej Kos Basel Alomair 150 1,148 0 22 Feb 2018
Differentially Private Generative Adversarial Network Liyang Xie Kaixiang Lin Shu Wang Fei Wang Jiayu Zhou SyDa 92 501 0 19 Feb 2018
Practical Secure Aggregation for Federated Learning on User-Held Data Keith Bonawitz Vladimir Ivanov Ben Kreuter Antonio Marcedone H. B. McMahan Sarvar Patel Daniel Ramage Aaron Segal Karn Seth FedML 83 506 0 14 Nov 2016
Communication-Efficient Learning of Deep Networks from Decentralized Data H. B. McMahan Eider Moore Daniel Ramage S. Hampson Blaise Agüera y Arcas FedML 406 17,593 0 17 Feb 2016

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.