Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning J Wang, C Xu, F Guzmán, A El-Kishky, Y Tang, BIP Rubinstein, T Cohn arXiv preprint arXiv:2107.05243, 2021 | 26 | 2021 |
Measuring and mitigating name biases in neural machine translation J Wang, B Rubinstein, T Cohn Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022 | 25 | 2022 |
Targeted poisoning attacks on black-box neural machine translation C Xu, J Wang, Y Tang, F Guzmán, BIP Rubinstein, T Cohn arXiv preprint arXiv:2011.00675, 2020 | 24* | 2020 |
As easy as 1, 2, 3: Behavioural testing of NMT systems for numerical translation J Wang, C Xu, F Guzmán, A El-Kishky, BIP Rubinstein, T Cohn arXiv preprint arXiv:2107.08357, 2021 | 7 | 2021 |
Mitigating backdoor poisoning attacks through the lens of spurious correlation X He, Q Xu, J Wang, B Rubinstein, T Cohn arXiv preprint arXiv:2305.11596, 2023 | 5 | 2023 |
Mitigating data poisoning in text classification with differential privacy C Xu, J Wang, F Guzmán, B Rubinstein, T Cohn Findings of the Association for Computational Linguistics: EMNLP 2021, 4348-4356, 2021 | 5 | 2021 |
IMBERT: Making BERT immune to insertion-based backdoor attacks X He, J Wang, B Rubinstein, T Cohn arXiv preprint arXiv:2305.16503, 2023 | 3 | 2023 |
Foiling Training-Time Attacks on Neural Machine Translation Systems J Wang, X He, B Rubinstein, T Cohn Findings of the Association for Computational Linguistics: EMNLP 2022, 5906-5913, 2022 | 1 | 2022 |
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning X He, J Wang, Q Xu, P Minervini, P Stenetorp, BIP Rubinstein, T Cohn arXiv preprint arXiv:2404.19597, 2024 | | 2024 |
Backdoor Attack on Multilingual Machine Translation J Wang, Q Xu, X He, BIP Rubinstein, T Cohn arXiv preprint arXiv:2404.02393, 2024 | | 2024 |
Detecting Backdoors in Deep Text Classifiers Y Guo, J Wang, T Cohn arXiv preprint arXiv:2210.11264, 2022 | | 2022 |