| Autor: |
Hisamoto, Sorami, Post, Matt, Duh, Kevin |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
Tansactions of the Association for Computational Linguistics (TACL) Volume 8, 2020 p.49-63 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1162/tacl_a_00299 |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
