Jun Wang

18 papers A* 2Journal 10Unranked 6
YearRankTypeTitle / Venue / Authors
2024 J jnl
Backdoor Attack on Multilingual Machine Translation.
CoRR
Jun Wang, Qiongkai Xu, Xuanli He, Benjamin I. P. Rubinstein, Trevor Cohn
2024 — conf
Backdoor Attacks on Multilingual Machine Translation.
NAACL-HLT
Jun Wang, Qiongkai Xu, Xuanli He, Benjamin I. P. Rubinstein, Trevor Cohn
2024 J jnl
Don't Throw Away Data: Better Sequence Knowledge Distillation.
CoRR
Jun Wang, Eleftheria Briakou, Hamid Dadkhahi, Rishabh Agarwal, Colin Cherry, Trevor Cohn
2024 J jnl
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks.
CoRR
Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2024 J jnl
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks.
Trans. Assoc. Comput. Linguistics
Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2023 J jnl
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks.
CoRR
Xuanli He, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2023 A* conf
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation.
EMNLP
Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2023 J jnl
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation.
CoRR
Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2022 J jnl
Detecting Backdoors in Deep Text Classifiers.
CoRR
You Guo, Jun Wang, Trevor Cohn
2022 — conf
Foiling Training-Time Attacks on Neural Machine Translation Systems.
EMNLP (Findings)
Jun Wang, Xuanli He, Benjamin I. P. Rubinstein, Trevor Cohn
2022 — conf
Measuring and Mitigating Name Biases in Neural Machine Translation.
ACL (1)
Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn
2021 A* conf
A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning.
WWW
Chang Xu, Jun Wang, Yuqing Tang, Francisco Guzmán, Benjamin I. P. Rubinstein, Trevor Cohn
2021 — conf
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation.
ACL/IJCNLP (Findings)
Jun Wang, Chang Xu, Francisco Guzmán, Ahmed El-Kishky, Benjamin I. P. Rubinstein, Trevor Cohn
2021 J jnl
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation.
CoRR
Jun Wang, Chang Xu, Francisco Guzmán, Ahmed El-Kishky, Benjamin I. P. Rubinstein, Trevor Cohn
2021 — conf
Mitigating Data Poisoning in Text Classification with Differential Privacy.
EMNLP (Findings)
Chang Xu, Jun Wang, Francisco Guzmán, Benjamin I. P. Rubinstein, Trevor Cohn
2021 — conf
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning.
ACL/IJCNLP (Findings)
Jun Wang, Chang Xu, Francisco Guzmán, Ahmed El-Kishky, Yuqing Tang, Benjamin I. P. Rubinstein, Trevor Cohn
2021 J jnl
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning.
CoRR
Jun Wang, Chang Xu, Francisco Guzmán, Ahmed El-Kishky, Yuqing Tang, Benjamin I. P. Rubinstein, Trevor Cohn
2020 J jnl
Targeted Poisoning Attacks on Black-Box Neural Machine Translation.
CoRR
Chang Xu, Jun Wang, Yuqing Tang, Francisco Guzmán, Benjamin I. P. Rubinstein, Trevor Cohn