About

I am an Assistant Professor on Research-Track in the Department of Electrical and Computer Engineering (ECE) at National University of Singapore (NUS), and an Associate Professor (Adjunct) in the School of CSE at Huazhong University of Science and Technology (HUST). My research lies at the intersection of Trustworthy AI and Secure & Private Software Engineering.

Specifically, I focus on the safety and ethics assessment, interpretability, and explainability of large language models (LLMs), as well as program analysis and vulnerability detection for modern software systems. More recently, I work on agentic system assurance—testing, verifying, and safeguarding LLM-based agents and multi-agent systems. I aim to build AI systems and software that are robust, transparent, and trustworthy.

I received my Ph.D. from the School of Computing, National University of Singapore (NUS) and my Bachelor's degree (First Class Honours) from Nanyang Technological University (NTU). Prior to joining HUST, I was a Research Fellow/Postdoctoral Researcher at NUS (2021–2023).

I am looking for motivated PhD/Master students and research interns. Please feel free to reach out if you are interested in working with me.


Research Interests

Trustworthy AI / LLM Safety LLM Interpretability & Explainability Program Analysis

News

  • Pinned Our SSRC-thematic grant (2026–2030) “debiaSING: Finding and Fixing Biases in the Human-AI Complex” has been awarded. We are looking for RAs and RFs hosted at the National University of Singapore. Please send your CV if you are interested!
  • Sep 2026 Join the Department of Electrical and Computer Engineering (ECE) at the National University of Singapore (NUS) as an Assistant Professor on Research-Track.
  • Aug 2026 Paper Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning accepted by TSE. Congratulations to Ningke and Yahui!
  • Aug 2026 Paper RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs accepted by EMNLP 2026 (main). Congratulations to Zhibo!
  • Jun 2026 Paper A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation accepted by ISSTA 2026. Congratulations to Shide!
  • May 2026 Joined the Program Committee of FSE 2027.
  • Apr 2026 Paper Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints accepted by ICMR 2026. Congratulations to Guanyu!
  • Apr 2026 Three papers accepted by ICPR 2026.
  • Apr 2026 Paper R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling accepted by ACL 2026 (main). Congratulations to Aijia!
  • Mar 2026 Paper Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics accepted by TIFS. Congratulations to Shide!
  • Mar 2026 Paper A Large-Scale Privacy Assessment of Android Third-Party SDKs accepted by TSE. Congratulations to Mark!
  • Feb 2026 Paper Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models accepted by ICASSP 2026 (oral). Congratulations to Fan!
  • Feb 2026 Joined the Program Committee of ICSE 2027.
  • Dec 2025 Two papers accepted by ICSE 2026. Congratulations to Xinyi!
  • Nov 2025 Two papers accepted by AAAI 2026.
  • Sep 2025 Survey paper Large language models for cyber security accepted by TOSEM. Congratulations to Hanxiang!
  • Jul 2025 Paper SPOLRE accepted by TOSEM. Congratulations to Guanyu and Yi!
  • Jun 2025 Joined the Program Committee of FSE 2026.
  • Mar 2025 Paper NeuSemSlice accepted by TOSEM. Congratulations to Shide!
  • Jan 2025 Two papers accepted by ICSE 2025. Congratulations to Shide and Yuqing!
  • Dec 2024 Serving as the Publication Chair for IWQoS 2025.
  • Dec 2024 Paper MiniScope accepted by TOSEM. Congratulations to Shenao!
  • Aug 2024 Survey paper Large Language Models for Software Engineering accepted by TOSEM. Congratulations to Xinyi!
  • Aug 2024 Two papers (full) accepted by ASE 2024 Industry Showcase Track. Congratulations to Xinyi, Jian and Shenao!
  • Aug 2024 Serving as a PC member for WWW 2025.
  • Aug 2024 Two papers accepted by ASE 2024. Congratulations to Baijun, Zhibo and Yuxi!
  • Jun 2024 Paper Drowzee accepted by OOPSLA 2024. Congratulations to Ningke!
  • Feb 2024 Paper MeTMaP accepted by FORGE 2024. Congratulations to Guanyu and Yi!
  • Feb 2024 Two papers accepted by WWW 2024. Congratulations to Liuhuo!
  • Jan 2024 Paper Glitch Tokens in Large Language Models accepted by FSE 2024. Congratulations to Yuxi and Yi!
  • Jan 2024 Paper Beyond Fidelity accepted by TOSEM. Congratulations to Baijun!
  • Jan 2024 Serving as PC member for WWW, LCTES, FORGE, Internetware, ICECCS 2024.

Publications

# corresponding author

2026
P34
Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning TSE '26
Ningke Li, Yahui Song, Kailong Wang#, Yuekang Li, Ling Shi, Yi Liu, Haoyu Wang
IEEE Transactions on Software Engineering (TSE), 2026.
Paper 
@article{li2026detecting,
  author    = {Li, Ningke and Song, Yahui and Li, Yuekang and Shi, Ling and Liu, Yi and Wang, Haoyu and Wang, Kailong},
  title     = {{Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning}},
  journal   = {IEEE Transactions on Software Engineering},
  pages     = {1--18},
  year      = {2026},
  publisher = {IEEE},
  doi       = {10.1109/TSE.2026.3731191}
}
P33
RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs EMNLP '26
Zhibo Zhang, Yuxi Li, Zhen Ouyang, Ling Shi, Kailong Wang#
In Proc. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026. (Main)
Paper 
@inproceedings{zhang2026raset,
  author    = {Zhang, Zhibo and Li, Yuxi and Ouyang, Zhen and Shi, Ling and Wang, Kailong},
  title     = {{RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs}},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2026},
  publisher = {Association for Computational Linguistics},
  note      = {To appear}
}
P32
A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation ISSTA '26
Shide Zhou, Kailong Wang#, Ling Shi, Haoyu Wang
In Proc. ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA), 2026.
Paper 
@inproceedings{zhou2026temporal,
  author    = {Zhou, Shide and Wang, Kailong and Shi, Ling and Wang, Haoyu},
  title     = {{A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation}},
  booktitle = {Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA)},
  year      = {2026},
  publisher = {ACM}
}
P31
Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints ICMR '26
Guanyu Wang, Kailong Wang#, Yihao Huang, Mingyi Zhou, Qing Zhang, Geguang Pu, Li Li
In Proc. ACM International Conference on Multimedia Retrieval (ICMR), 2026.
Paper 
@inproceedings{wang2026privacy,
  author    = {Wang, Guanyu and Wang, Kailong and Huang, Yihao and Zhou, Mingyi and Pu, Geguang and Li, Li},
  title     = {{Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints}},
  booktitle = {Proceedings of the 2026 International Conference on Multimedia Retrieval},
  pages     = {2003--2011},
  year      = {2026},
  publisher = {ACM},
  doi       = {10.1145/3805622.3810856}
}
P30
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling ACL '26
Aijia Cheng, Kailong Wang, Ling Shi, Yongxin Zhao
In Proc. Annual Meeting of the Association for Computational Linguistics (ACL), 2026.
Paper 
@inproceedings{cheng2026r2if,
  author    = {Cheng, Aijia and Wang, Kailong and Shi, Ling and Zhao, Yongxin},
  title     = {{R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling}},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages     = {36995--37008},
  year      = {2026},
  publisher = {Association for Computational Linguistics},
  doi       = {10.18653/v1/2026.acl-long.1715}
}
P29
Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics TIFS '26
Shide Zhou, Kailong Wang#, Ling Shi, Haoyu Wang
IEEE Transactions on Information Forensics and Security (TIFS), 2026.
Paper 
@article{zhou2026exposing,
  author    = {Zhou, Shide and Wang, Kailong and Shi, Ling and Wang, Haoyu},
  title     = {{Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics}},
  journal   = {IEEE Transactions on Information Forensics and Security},
  volume    = {21},
  pages     = {4074--4089},
  year      = {2026},
  publisher = {IEEE},
  doi       = {10.1109/TIFS.2026.3683279}
}
P28
A Large-Scale Privacy Assessment of Android Third-Party SDKs TSE '26
Mark Huasong Meng, Chuan Yan, Yun Hao, Qing Zhang, Zeyu Wang, Kailong Wang, Sin Gee Teo, Guangdong Bai, Jin Song Dong
IEEE Transactions on Software Engineering (TSE), 2026.
Paper 
@article{meng2026assessing,
  author    = {Meng, Mark Huasong and Yan, Chuan and Zhang, Qing and Wang, Zeyu and Wang, Kailong and Teo, Sin G. and Bai, Guangdong and Dong, Jin Song},
  title     = {{Assessing Privacy Disclosure Compliance of Android Third-Party SDKs}},
  journal   = {IEEE Transactions on Software Engineering},
  volume    = {52},
  number    = {7},
  pages     = {1995--2012},
  year      = {2026},
  publisher = {IEEE},
  doi       = {10.1109/TSE.2026.3676979}
}
P27
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models ICASSP '26
Fan Yang, Yihao Huang, Ling Shi, Geguang Pu, Kailong Wang#
In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026. (Oral)
Paper 
@inproceedings{yang2026efficient,
  author    = {Yang, Fan and Huang, Yihao and Shi, Ling and Pu, Geguang and Wang, Kailong},
  title     = {{Efficient and Effective Universal Adversarial Attack Against Vision-Language Pre-Training Models}},
  booktitle = {ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages     = {1536--1540},
  year      = {2026},
  publisher = {IEEE},
  doi       = {10.1109/ICASSP55912.2026.11464209}
}
P26
Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving ICSE '26
Xinyi Zheng, Ningke Li, Xiaokun Luan, Kailong Wang#, Ling Shi, Meng Sun, Haoyu Wang
In Proc. IEEE/ACM International Conference on Software Engineering (ICSE), 2026.
Paper 
@inproceedings{zheng2026correctness,
  author    = {Zheng, Xinyi and Li, Ningke and Luan, Xiaokun and Wang, Kailong and Shi, Ling and Sun, Meng and Wang, Haoyu},
  title     = {{Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving}},
  booktitle = {2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE)},
  year      = {2026},
  publisher = {IEEE}
}
P25
ADARULE: LLM-Driven Natural Language to LTL Conversion via Pattern-Adaptive Rule Induction ICSE '26
Jiayi Hu, Jingling Sun, Chong Wang, Yihao Huang, Jincao Feng, Yilongfei Xu, Yong Li, Kailong Wang, Weikai Miao, Jin Song Dong, Geguang Pu
In Proc. IEEE/ACM International Conference on Software Engineering (ICSE), 2026.
@inproceedings{hu2026adarule,
  author    = {Hu, Jiayi and Sun, Jingling and Wang, Chong and Huang, Yihao and Feng, Jincao and Xu, Yilongfei and Li, Yong and Wang, Kailong and Miao, Weikai and Dong, Jin Song and Pu, Geguang},
  title     = {{ADARULE: LLM-Driven Natural Language to LTL Conversion via Pattern-Adaptive Rule Induction}},
  booktitle = {2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE)},
  year      = {2026},
  publisher = {IEEE}
}
P24
STEAMROLLER: A Multi-Agent System for Inclusive Automatic Speech Recognition for People who Stutter AAAI '26
Ziqi Xu, Yi Liu, Yuekang Li, Ling Shi, Kailong Wang, Yongxin Zhao
In Proc. AAAI Conference on Artificial Intelligence (AAAI), 2026.
Paper 
@article{xu2026steamroller,
  author    = {Xu, Ziqi and Liu, Yi and Li, Yuekang and Shi, Ling and Wang, Kailong and Zhao, Yongxin},
  title     = {{STEAMROLLER: A Multi-Agent System for Inclusive Automatic Speech Recognition for People Who Stutter}},
  journal   = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume    = {40},
  number    = {46},
  pages     = {39495--39503},
  year      = {2026},
  publisher = {AAAI Press},
  doi       = {10.1609/aaai.v40i46.41300}
}
P23
On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks AAAI '26
Ting Bi, Chenghang Ye, Zheyu Yang, Ziyi Zhou, Cui Tang, Zui Tao, Jun Zhang, Kailong Wang, Liting Zhou, Yang Yang, Tianlong Yu
In Proc. AAAI Conference on Artificial Intelligence (AAAI), 2026.
Paper 
@article{bi2026feasibility,
  author    = {Bi, Ting and Ye, Chenghang and Yang, Zheyu and Zhou, Ziyi and Tang, Cui and Tao, Zui and Zhang, Jun and Wang, Kailong and Zhou, Liting and Yang, Yang and Yu, Tianlong},
  title     = {{On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks}},
  journal   = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume    = {40},
  number    = {45},
  pages     = {38252--38260},
  year      = {2026},
  publisher = {AAAI Press},
  doi       = {10.1609/aaai.v40i45.41164}
}
2025
P22
Large Language Models for Cyber Security: A Systematic Literature Review TOSEM '25
Hanxiang Xu, Shenao Wang, Ningke Li, Kailong Wang#, Yanjie Zhao, Kai Chen, Ting Yu, Yang Liu, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 2025.
Paper 
@article{xu2025large,
  author    = {Xu, Hanxiang and Wang, Shenao and Li, Ningke and Wang, Kailong and Zhao, Yanjie and Chen, Kai and Yu, Ting and Liu, Yang and Wang, Haoyu},
  title     = {{Large Language Models for Cyber Security: A Systematic Literature Review}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  year      = {2025},
  publisher = {ACM},
  doi       = {10.1145/3769676}
}
P21
SEAR: A Multimodal Dataset for Analyzing AR-LLM-Driven Social Engineering Behaviors ACM MM '25
Tianlong Yu, Chenghang Ye, Zheyu Yang, Ziyi Zhou, Cui Tang, Zui Tao, Jun Zhang, Kailong Wang, Liting Zhou, Yang Yang, Ting Bi
In Proc. ACM International Conference on Multimedia (ACM MM), 2025.
Paper 
@inproceedings{yu2025sear,
  author    = {Yu, Tianlong and Ye, Chenghang and Yang, Zheyu and Zhou, Ziyi and Tang, Cui and Tao, Zui and Zhang, Jun and Wang, Kailong and Zhou, Liting and Yang, Yang and Bi, Ting},
  title     = {{SEAR: A Multimodal Dataset for Analyzing AR-LLM-Driven Social Engineering Behaviors}},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
  pages     = {12981--12987},
  year      = {2025},
  publisher = {ACM},
  doi       = {10.1145/3746027.3758245}
}
P20
SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing TOSEM '25
Yi Liu, Guanyu Wang, Xinyi Zheng, Gelei Deng, Kailong Wang#, Yang Liu, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 2025.
Paper 
@article{liu2026spolre,
  author    = {Liu, Yi and Wang, Guanyu and Zheng, Xinyi and Deng, Gelei and Wang, Kailong and Liu, Yang and Wang, Haoyu},
  title     = {{SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  volume    = {35},
  number    = {5},
  pages     = {1--25},
  year      = {2026},
  publisher = {ACM},
  doi       = {10.1145/3748306}
}
P19
Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods ICML '25
Yedi Zhang, Yufan Cai, Xinyue Zuo, Xiaokun Luan, Kailong Wang, Zhe Hou, Yifan Zhang, Zhiyuan Wei, Meng Sun, Jun Sun, Jing Sun, Jin Song Dong
In Proc. International Conference on Machine Learning (ICML), 2025.
Paper 
@inproceedings{zhang2025position,
  author    = {Zhang, Yedi and Cai, Yufan and Zuo, Xinyue and Luan, Xiaokun and Wang, Kailong and Hou, Zhe and Zhang, Yifan and Wei, Zhiyuan and Sun, Meng and Sun, Jun and Sun, Jing and Dong, Jin Song},
  title     = {{Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods}},
  booktitle = {Proceedings of the 42nd International Conference on Machine Learning (ICML)},
  series    = {Proceedings of Machine Learning Research},
  volume    = {267},
  pages     = {82441--82459},
  year      = {2025},
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v267/zhang25ds.html}
}
P18
NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing TOSEM '25
Shide Zhou, Tianlin Li, Kailong Wang#, Yihao Huang, Ling Shi, Yang Liu, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 2025.
Paper 
@article{zhou2025neusemslice,
  author    = {Zhou, Shide and Li, Tianlin and Huang, Yihao and Shi, Ling and Wang, Kailong and Liu, Yang and Wang, Haoyu},
  title     = {{NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-Level Semantic Slicing}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  volume    = {35},
  number    = {1},
  pages     = {1--27},
  year      = {2025},
  publisher = {ACM},
  doi       = {10.1145/3731556}
}
P17
Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks ICSE '25
Shide Zhou, Tianlin Li, Kailong Wang#, Yihao Huang, Ling Shi, Yang Liu, Haoyu Wang
In Proc. IEEE/ACM International Conference on Software Engineering (ICSE), 2025.
Paper 
@inproceedings{zhou2025understanding,
  author    = {Zhou, Shide and Li, Tianlin and Wang, Kailong and Huang, Yihao and Shi, Ling and Liu, Yang and Wang, Haoyu},
  title     = {{Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks}},
  booktitle = {2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)},
  pages     = {730--742},
  year      = {2025},
  publisher = {IEEE},
  doi       = {10.1109/ICSE55347.2025.00209}
}
P16
Decoding Secret Memorization in Code LLMs Through Token-Level Characterization ICSE '25
Yuqing Nie, Chong Wang, Kailong Wang#, Guoai Xu, Guosheng Xu, Haoyu Wang
In Proc. IEEE/ACM International Conference on Software Engineering (ICSE), 2025.
Paper 
@inproceedings{nie2025decoding,
  author    = {Nie, Yuqing and Wang, Chong and Wang, Kailong and Xu, Guoai and Xu, Guosheng and Wang, Haoyu},
  title     = {{Decoding Secret Memorization in Code LLMs Through Token-Level Characterization}},
  booktitle = {2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)},
  pages     = {2880--2892},
  year      = {2025},
  publisher = {IEEE},
  doi       = {10.1109/ICSE55347.2025.00229}
}
2024
P15
MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis TOSEM '24
Shenao Wang, Yuekang Li, Kailong Wang#, Yi Liu, Hui Li, Yang Liu, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 2024.
Paper 
@article{wang2025miniscope,
  author    = {Wang, Shenao and Li, Yuekang and Wang, Kailong and Liu, Yi and Li, Hui and Liu, Yang and Wang, Haoyu},
  title     = {{MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  volume    = {34},
  number    = {6},
  pages     = {1--29},
  year      = {2025},
  publisher = {ACM},
  doi       = {10.1145/3709351}
}
P14
Large Language Models for Software Engineering: A Systematic Literature Review TOSEM '24
Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 2024.
Paper 
@article{hou2024large,
  author    = {Hou, Xinyi and Zhao, Yanjie and Liu, Yue and Yang, Zhou and Wang, Kailong and Li, Li and Luo, Xiapu and Lo, David and Grundy, John and Wang, Haoyu},
  title     = {{Large Language Models for Software Engineering: A Systematic Literature Review}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  volume    = {33},
  number    = {8},
  pages     = {1--79},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3695988}
}
P13
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models ASE '24
Zhibo Zhang, Wuxia Bai, Yuxi Li, Mark Huasong Meng, Kailong Wang#, Ling Shi, Li Li, Jun Wang, Haoyu Wang
In Proc. IEEE/ACM International Conference on Automated Software Engineering (ASE), 2024.
Paper 
@inproceedings{zhang2024glitchprober,
  author    = {Zhang, Zhibo and Bai, Wuxia and Li, Yuxi and Meng, Mark Huasong and Wang, Kailong and Shi, Ling and Li, Li and Wang, Jun and Wang, Haoyu},
  title     = {{GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models}},
  booktitle = {Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering},
  pages     = {643--655},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3691620.3695060}
}
P12
Semantic-Enhanced Indirect Call Analysis with Large Language Models ASE '24
Baijun Cheng, Cen Zhang, Kailong Wang#, Ling Shi, Yang Liu, Haoyu Wang, Yao Guo, Xiangqun Chen
In Proc. IEEE/ACM International Conference on Automated Software Engineering (ASE), 2024.
Paper 
@inproceedings{cheng2024semanticenhanced,
  author    = {Cheng, Baijun and Zhang, Cen and Wang, Kailong and Shi, Ling and Liu, Yang and Wang, Haoyu and Guo, Yao and Li, Ding and Chen, Xiangqun},
  title     = {{Semantic-Enhanced Indirect Call Analysis with Large Language Models}},
  booktitle = {Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering},
  pages     = {430--442},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3691620.3695016}
}
P11
Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments ASE '24
Xinyi Zheng, Chen Wei, Shenao Wang, Yanjie Zhao, Peiming Gao, Yuanchao Zhang, Kailong Wang#, Haoyu Wang
In Proc. IEEE/ACM International Conference on Automated Software Engineering, Industry Showcase (ASE), 2024.
Paper 
@inproceedings{zheng2024robust,
  author    = {Zheng, Xinyi and Wei, Chen and Wang, Shenao and Zhao, Yanjie and Gao, Peiming and Zhang, Yuanchao and Wang, Kailong and Wang, Haoyu},
  title     = {{Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments}},
  booktitle = {Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering},
  pages     = {1990--2001},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3691620.3695262}
}
P10
Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs ASE '24
Jian Zhao, Shenao Wang, Yanjie Zhao, Xinyi Hou, Kailong Wang, Peiming Gao, Yuanchao Zhang, Chen Wei, Haoyu Wang
In Proc. IEEE/ACM International Conference on Automated Software Engineering, Industry Showcase (ASE), 2024.
Paper 
@inproceedings{zhao2024models,
  author    = {Zhao, Jian and Wang, Shenao and Zhao, Yanjie and Hou, Xinyi and Wang, Kailong and Gao, Peiming and Zhang, Yuanchao and Wei, Chen and Wang, Haoyu},
  title     = {{Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs}},
  booktitle = {Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering},
  pages     = {2087--2098},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3691620.3695271}
}
P9
Drowzee: Metamorphic Testing for Fact-conflicting Hallucination Detection in Large Language Models OOPSLA '24
Ningke Li, Yuekang Li, Yi Liu, Ling Shi, Kailong Wang#, Haoyu Wang
In Proc. ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages & Applications (OOPSLA), 2024.
Paper 
@article{li2024drowzee,
  author    = {Li, Ningke and Li, Yuekang and Liu, Yi and Shi, Ling and Wang, Kailong and Wang, Haoyu},
  title     = {{Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models}},
  journal   = {Proceedings of the ACM on Programming Languages},
  volume    = {8},
  number    = {OOPSLA2},
  pages     = {1843--1872},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3689776}
}
P8
Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection FSE '24
Yuxi Li, Yi Liu, Gelei Deng, Ying Zhang, Wenjia Song, Ling Shi, Kailong Wang#, Yuekang Li, Yang Liu, Haoyu Wang
In Proc. ACM International Conference on the Foundations of Software Engineering (FSE), 2024.
Paper 
@article{li2024glitch,
  author    = {Li, Yuxi and Liu, Yi and Deng, Gelei and Zhang, Ying and Song, Wenjia and Shi, Ling and Wang, Kailong and Li, Yuekang and Liu, Yang and Wang, Haoyu},
  title     = {{Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection}},
  journal   = {Proceedings of the ACM on Software Engineering},
  volume    = {1},
  number    = {FSE},
  pages     = {2075--2097},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3660799}
}
P7
MetMap: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation FORGE '24
Guanyu Wang, Yuekang Li, Yi Liu, Gelei Deng, Tianlin Li, Guosheng Xu, Yang Liu, Haoyu Wang, Kailong Wang#
In Proc. AI Foundation Models and Software Engineering (FORGE), 2024.
Paper 
@inproceedings{wang2024metmap,
  author    = {Wang, Guanyu and Li, Yuekang and Liu, Yi and Deng, Gelei and Li, Tianlin and Xu, Guosheng and Liu, Yang and Wang, Haoyu and Wang, Kailong},
  title     = {{MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation}},
  booktitle = {Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering},
  pages     = {12--23},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3650105.3652297}
}
P6
Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors TOSEM '24
Baijun Cheng, Shengming Zhao, Kailong Wang#, Meizhen Wang, Guangdong Bai, Ruitao Feng, Yao Guo, Lei Ma, Haoyu Wang
ACM Transactions on Software Engineering and Methodology (TOSEM), 33(5):1–33, 2024.
Paper 
@article{cheng2024fidelity,
  author    = {Cheng, Baijun and Zhao, Shengming and Wang, Kailong and Wang, Meizhen and Bai, Guangdong and Feng, Ruitao and Guo, Yao and Ma, Lei and Wang, Haoyu},
  title     = {{Beyond Fidelity: Explaining Vulnerability Localization of Learning-Based Detectors}},
  journal   = {ACM Transactions on Software Engineering and Methodology},
  volume    = {33},
  number    = {5},
  pages     = {1--33},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3641543}
}
P5
Don't Bite Off More Than You Can Chew: Investigating Excessive Permission Requests in Trigger-action Integrations WWW '24
Liuhuo Wan, Kailong Wang#, Kulani Tharaka Mahadewa, Haoyu Wang, Guangdong Bai
In Proc. ACM Web Conference (WWW), 2024.
Paper 
@inproceedings{wan2024don,
  author    = {Wan, Liuhuo and Wang, Kailong and Mahadewa, Kulani and Wang, Haoyu and Bai, Guangdong},
  title     = {{Don't Bite Off More than You Can Chew: Investigating Excessive Permission Requests in Trigger-Action Integrations}},
  booktitle = {Proceedings of the ACM Web Conference 2024},
  pages     = {3106--3116},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3589334.3645721}
}
P4
Is It Safe To Share Your Files? An Empirical Security Analysis of Google Workspace WWW '24
Liuhuo Wan, Kailong Wang#, Haoyu Wang, Guangdong Bai
In Proc. ACM Web Conference (WWW), 2024.
Paper 
@inproceedings{wan2024safe,
  author    = {Wan, Liuhuo and Wang, Kailong and Wang, Haoyu and Bai, Guangdong},
  title     = {{Is It Safe to Share Your Files? An Empirical Security Analysis of Google Workspace}},
  booktitle = {Proceedings of the ACM Web Conference 2024},
  pages     = {1892--1901},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3589334.3645697}
}
P3
Masterkey: Automated Jailbreak of Multiple Large Language Model Chatbots NDSS '24
Gelei Deng, Yi Liu, Yuekang Li, Kailong Wang, Ying Zhang, Zefeng Li, Haoyu Wang, Tianwei Zhang, Yang Liu
In Proc. Network and Distributed System Security Symposium (NDSS), 2024.
Paper 
@inproceedings{deng2024masterkey,
  author    = {Deng, Gelei and Liu, Yi and Li, Yuekang and Wang, Kailong and Zhang, Ying and Li, Zefeng and Wang, Haoyu and Zhang, Tianwei and Liu, Yang},
  title     = {{MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots}},
  booktitle = {Proceedings 2024 Network and Distributed System Security Symposium},
  year      = {2024},
  publisher = {Internet Society},
  doi       = {10.14722/ndss.2024.24188}
}
P2
Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning NDSS-AISCC '24
Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu
In Proc. NDSS Workshop on AI System with Confidential Computing (AISCC), 2024.
Paper 
@inproceedings{deng2024pandora,
  author    = {Deng, Gelei and Liu, Yi and Wang, Kailong and Li, Yuekang and Zhang, Tianwei and Liu, Yang},
  title     = {{PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning}},
  booktitle = {Proceedings 2024 Workshop on AI Systems with Confidential Computing},
  year      = {2024},
  publisher = {Internet Society},
  doi       = {10.14722/aiscc.2024.23018}
}
P1
Essential or Excessive? MindaExt: Measuring Data Minimization Practices among Browser Extensions SANER '24
Yuxi Ling, Yun Hao, Yuyan Wang, Kailong Wang, Guangdong Bai, Jin Song Dong
In Proc. IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2024.
PDF 
@inproceedings{ling2024excessive,
  author    = {Ling, Yuxi and Hao, Yun and Wang, Yuyan and Wang, Kailong and Bai, Guangdong and Dong, Jin Song},
  title     = {{Essential or Excessive? MINDAEXT: Measuring Data Minimization Practices among Browser Extensions}},
  booktitle = {2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)},
  pages     = {964--975},
  year      = {2024},
  publisher = {IEEE},
  doi       = {10.1109/SANER60148.2024.00104}
}

For a complete list, see Google Scholar or DBLP.

Education

  • 2016–2022
    Ph.D. in Computer Science
    School of Computing, National University of Singapore (NUS), Singapore
  • 2011–2015
    B.Eng. in Infocommunication Engineering, First Class Honours (GPA 4.76/5.00)
    School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore

Experience

  • 2026–now
    Assistant Professor on Research-Track
    Department of Electrical and Computer Engineering (ECE), National University of Singapore (NUS)
  • 2023–now
    Associate Professor (Adjunct)
    School of CSE, Huazhong University of Science and Technology (HUST)
  • 2022–2023
    Postdoctoral Research Fellow
    School of Computing, National University of Singapore (NUS) · Supervised by Prof. Jin Song Dong
  • 2019
    Visiting Scholar
    University of Queensland, Australia
  • 2015–2021
    Research Assistant
    School of Computing, National University of Singapore (NUS) · Supervised by Prof. Jin Song Dong

Academic Service

Journal Editorship / Reviewer

  • IEEE Transactions on Software Engineering (TSE)
  • ACM Transactions on Software Engineering and Methodology (TOSEM)
  • IEEE Transactions on Dependable and Secure Computing (TDSC)
  • Nature Communications (NC)
  • IEEE Transactions on Information Forensics and Security (TIFS)

Program Committee Member

  • ACM FSE 2027
  • IEEE/ACM ICSE 2027
  • ACM FSE 2026
  • AAAI 2026
  • ACM Web Conference (WWW 2023–2026)
  • ACM International Conference on Multimedia (MM 2025)
  • IEEE/ACM IWQoS 2025 (Publication Chair)
  • FORGE 2024–2025
  • Internetware 2024–2025
  • ICECCS 2024
  • ICFEM 2023
  • IEEE PRDC 2023
  • ChinaSoft 2023