I was a research fellow at the University of Melbourne, where I worked with Prof. Trevor Cohn and Prof. Benjamin Rubinstein on adversarial learning for natural language processing (NLP) (understanding vulnerabilities of various NLP systems). Prior to this, I was a CSIRO Early Research Career (CERC) postdoctoral fellow at CSIRO Data61, where I worked with Dr. Cecile Paris and others on opinion mining in social media. I obtained PhD in Computer Science from Nanyang Technological University, under the supervision of Assoc Prof. Jie Zhang, and a master degree from the University of Chinese Academy of Sciences.

• My research interests lie in the general area of natural language processing, artificial intelligence, and cybersecurity, particularly in developing explainable and robust models for various NLP tasks (e.g., text classification and machine translation). I am also interested in machine learning and deep learning techniques applied to those tasks. [Google Scholar]

Recent News

• May 2021: our two papers “Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning” and “As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation” were accepted by ACL 2021.
• Jan 2021: our paper “A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning” was accepted by WWW 2021.
• July 2020: our paper “Assessing Social License to Operate from the Public Discourse on Social Media” was accepted by COLING 2020.
• March 2020: our paper “DeepMnemonic: Password Mnemonic Generation via Deep Attentive Encoder-Decoder Model” was accepted by TDSC 2020.
• Jan 2020: our paper “DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains” was accepted by ECAI 2020.
• August 2019: Our paper “STRIP: A Defence Against Trojan Attacks on Deep Neural Networks” was accepted by ACSAC 2019.
• May 2019: Our paper “Recognising Agreement and Disagreement between Stances with Reason Comparing Networks” was accepted by ACL 2019.
• May 2018: Our paper “Cross-Target Stance Classification with Self-Attention Networks” was accepted by ACL 2018.
• April 2017: Our paper “Online Reputation Fraud Campaign Detection in User Ratings” was accepted by IJCAI 2017.
• Feb 2017: Our paper “Large-Scale Wi-Fi Hotspot Classification via Deep Learning” was accepted as a poster by WWW 2017.
• Aug 2015: Our paper “Towards Collusive Fraud Detection in Online Reviews” was accepted by IEEE ICDM 2015.
• Jan 2015: Our paper “Combating Product Review Spam Campaigns via Multiple Heterogeneous Pairwise Features” was accepted by SIAM SDM 2015.