# Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?

## TL;DR

This paper investigates the vulnerability of sequence-to-sequence models, like those used in machine translation, to membership inference attacks, revealing potential privacy risks in machine learning services.

## Contribution

It introduces the membership inference problem for sequence generation, provides an open dataset, and reports initial attack results on state-of-the-art models.

## Key findings

- Models leak private information against inference attacks
- Open dataset enables further research in this area
- Initial results show vulnerability of sequence-to-sequence models

## 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.