Scholar

Yan Xiao

Google Scholar ID: rSL_uscAAAAJ

Sun Yat-sen University

software engineeringdeep learning

Citations & Impact

All-time

Citations

1,542

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

- Papers accepted by ACL2025, IJCAI2025, ICSE2025, TOSEM, NN, TIFS, ASE2023, TSE, SPE, IEEE Transactions on Industrial Informatics, ASE, TDSC, IST, etc.
- Topics covered include multi-task adversarial attacks, quantum-classical hybrid poisoning attack detection method, deep reinforcement learning implementations, fuzzing testing, Transformer-based models for SE, backdoor attacks against speech recognition, NLP software testing, smart contract source code obfuscation, code smell detection, anomaly detection using a semi-supervised approach, distinguishing input data for DNNs, detecting anomalies and adversaries for DNNs, adversarial robustness of DNNs, code-comment synchronization, predicting software defects, impact of distance metric on SMOTE-based techniques, complexity-based oversampling technique, self-checking system for DNNs

Research Experience

- Associate Professor at Sun Yat-sen University, Shenzhen, China, Jun. 2023 - now
- Research Fellow at National University of Singapore, Singapore, Nov. 2019 - May. 2023

Education

- Ph.D. in Computer Science from City University of Hong Kong, supervised by Prof. Jacky Keung
- Research Fellow at SoC, National University of Singapore, under the supervision of Prof. Jin Song Dong and Prof. David S. Rosenblum, and guided by Prof. Ivan Beschastnikh
- Started research career at Huawei Noah’s Ark Lab, mentored by Prof. Hong Xu and Dr. George Trimponias

Background

My current research focus is evaluating the trustworthiness of deep learning systems including trustworthiness evaluation for autonomous driving, deep neural network repair for improving the accuracy of models, input discrimination for deep learning systems. My research is within the domain of Software Engineering and Artificial Intelligence in application domains related to software bug localization, software code readability, software integration test, data mining, and big data analysis.

Miscellany