A voice impersonation system is trained by deceiving a white-box automatic speaker verification model, using an ASR model to preserve content, and it performs comparably to voice conversion trained on only a few target utterances.
Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in the context of sequence-to-sequence models, which are important in applications such as machine translation and video captioning. We define the membership inference problem for sequence generation, provide an open dataset based on state-of-the-art machine translation models, and report initial results on whether these models leak private information against several kinds of membership inference attacks.
fields
cs.SD 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
V2S attack: building DNN-based voice conversion from automatic speaker verification
A voice impersonation system is trained by deceiving a white-box automatic speaker verification model, using an ASR model to preserve content, and it performs comparably to voice conversion trained on only a few target utterances.