Speech Privacy Leakage from Shared Gradients in Distributed Learning. (arXiv:2302.10441v1 [cs.LG])

Distributed machine learning paradigms, such as federated learning, have been
recently adopted in many privacy-critical applications for speech analysis.
However, such frameworks are vulnerable to privacy leakage attacks from shared
gradients. Despite extensive efforts in the image domain, the exploration of
speech privacy leakage from gradients is quite limited. In this paper, we
explore methods for recovering private speech/speaker information from the
shared gradients in distributed learning settings. We conduct experiments on a
keyword spotting model with two different types …

analysis applications attacks critical distributed domain federated learning frameworks information machine machine learning privacy settings speech speech analysis vulnerable