@article{hisamoto-etal-2020-membership,
    title = "Membership Inference Attacks on Sequence-to-Sequence Models: {I}s My Data In Your Machine Translation System?",
    author = "Hisamoto, Sorami  and
      Post, Matt  and
      Duh, Kevin",
    editor = "Johnson, Mark  and
      Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "8",
    year = "2020",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.tacl-1.4/",
    doi = "10.1162/tacl_a_00299",
    pages = "49--63",
    abstract = "Data privacy is an important issue for {\textquotedblleft}machine learning as a service{\textquotedblright} 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."
}