Voiceblock: Privacy through real-time adversarial attacks with audio-to-audio models

P O'Reilly, A Bugler, K Bhandari… - Advances in Neural …, 2022 - proceedings.neurips.cc
As governments and corporations adopt deep learning systems to collect and analyze user-
generated audio data, concerns about security and privacy naturally emerge in areas such …

Breaking Security-Critical Voice Authentication

A Kassis, U Hengartner - 2023 IEEE Symposium on Security …, 2023 - ieeexplore.ieee.org
Voice authentication (VA) has recently become an integral part in numerous security-critical
operations, such as bank transactions and call center conversations. The vulnerability of …

Beyond neural-on-neural approaches to speaker gender protection

L van Bemmel, Z Liu, N Vaessen… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Recent research has proposed approaches that modify speech to defend against gender
inference attacks. The goal of these protection algorithms is to control the availability of …

[PDF][PDF] Beyond Neural-on-Neural Approaches to Speaker Gender Protection

Z Liu, N Vaessen, M Larson - 2023 - repository.ubn.ru.nl
Recent research has proposed approaches that modify speech to defend against gender
inference attacks. The goal of these protection algorithms is to control the availability of …