Chang Xu

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

Conference Proceedings  |  2021  |  Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these..

A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

Chang Xu, Jun Wang, Yuqing Tang, Francisco Guzman, Benjamin IP Rubinstein, Trevor Cohn

Conference Proceedings  |  2021  |  PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021)

As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutin..

DAN: Dual-view representation learning for adapting stance classifiers to new domains

C Xu, C Paris, S Nepal, R Sparks, C Long, Y Wang

Conference Proceedings  |  2020  |  Frontiers in Artificial Intelligence and Applications

Comments on the three-zone approach for social media monitoring

R Sparks, C Paris, A Joshi, C Xu

Journal article  |  2020  |  Quality Engineering

DeepMnemonic: Password Mnemonic Generation via Deep Attentive Encoder-Decoder Model

Yao Cheng, Chang Xu, Zhen Hai, Yingjiu Li

Journal article  |  2020  |  IEEE Transactions on Dependable and Secure Computing

Strong passwords are fundamental to the security of password-based user authentication systems. In recent years, much effort has b..

Recognising agreement and disagreement between stances with reason comparing networks

C Xu, C Paris, S Nepal, R Sparks

Conference Proceedings  |  2020  |  ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods foc..

STRIP: a defence against trojan attacks on deep neural networks

Yansong Gao, Change Xu, Derui Wang, Shiping Chen, Damith C Ranasinghe, Surya Nepal

Conference Proceedings  |  2019  |  Proceedings of the 35th Annual Computer Security Applications Conference

A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Trojan attacks expl..

Learning from bad data via generation

T Guo, C Xu, B Shi, C Xu, D Tao

Conference Proceedings  |  2019  |  Advances in Neural Information Processing Systems

Cross-target stance classification with self-attention networks

C Xu, C Paris, S Nepal, R Sparks

Conference Proceedings  |  2018  |  ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually tra..

Collusive Opinion Fraud Detection in Online Reviews

Chang Xu, Jie Zhang

Journal article  |  2017  |  ACM Transactions on the Web

We address the collusive opinion fraud problem in online review portals, where groups of people work together to deliver deceptive..