Published June 26, 2023
| Version v1
Other
Open
Targeted Adversarial Attacks against Neural Machine Translation
Authors/Creators
- 1. EPFL
- 2. University of British Columbia
- 3. Armasuisse S+T
Description
This upload contains the language models utilized in the paper "Targeted Adversarial Attacks against Neural Machine Translation". In this paper, we propose a targeted adversarial attack against NMT models by inserting a keyword to the translation.
These language models, along with their respective fully connected layers, are trained for Marian NMT models discussed in the paper. For further details on the implementation and usage of our attack, please refer to the official GitHub repository.