Chang Xu

A targeted attack on black-box neural machine translation with parallel data poisoning

C Xu, J Wang, Y Tang, F GuzmA¡n, BIP Rubinstein, T Cohn

Conference Proceedings  |  2021  |  The Web Conference 2021 - Proceedings of the World Wide Web Conference, 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

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..

Online Reputation Fraud Campaign Detection in User Ratings

Chang Xu, Jie Zhang, Zhu Sun

Conference Proceedings  |  2017  |  Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

Reputation fraud campaigns (RFCs) distort the reputations of rated items, by generating fake ratings through multiple spammers. On..

Large-Scale Wi-Fi Hotspot Classification via Deep Learning

Chang Xu, Kuiyu Chang, Khee-Chin Chua, Meishan Hu, Zhenxiang Gao

Conference Proceedings  |  2017  |  Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion