Yuexin Li

I am a first-year CS PhD student at National University of Singapore (NUS), closely working with Asst. Prof. Bryan Hooi. Previously, I have spent 2.5 years in NUS-NCS Joint Lab for Cyber Security, focusing on phishing detection and its real-world deployment. I also obtained my M.Comp. in Artificial Intelligence at NUS in 2023.

Before NUS, I received my B.Eng. in Computer Science and Technology at South China University of Technology in 2021, where I did research on evolutionary algorithms and urban computing under Prof. Zhi-Hui Zhan. I was fortunate to be a visiting student to University College London in 2019 and University of California, Berkeley in 2020.

Email: yuexinli [AT] u [DOT] nus [DOT] edu

CV / LinkedIn / Google Scholar / Github

Research

My current research interests mainly include integrating machine learning approaches to cybersecurity applications.

News

[2025/02] Invited to serve as a reviewer in ICLR 2025 Workshop on LLM Reasoning and Planning.
[2025/02] Invited to serve as a reviewer in IEEE T-IFS.
[2025/01] Our work on phishing detection system deployment is accepted by WWW 2025 (Demo Track).
[2025/01] I start my PhD study at NUS.
[2024/12] Our work on MLLM agent-based phishing detection is accepted by AAAI 2025.
[2024/06] Our work on knowledge-aware multimodal phishing detection is accepted by USENIX Security 2024.
[2024/04] Invited to give a talk 'Towards Data-centric Multimodal Phishing Detection' at the United Nations-Singapore Cyber Fellowship Program.
[2023/08] Invited to give a talk 'Towards Data-centric Phishing Detection' to China Mobile.
[2023/03] I earn my Master of Computing degree in NUS.
[2022/08] I join NUS-NCS Joint Laboratory for Cyber Security as a full-time Research Assistant.

Publications

	PhishIntel: Toward Practical Deployment of Reference-based Phishing Detection Yuexin Li, Hiok Kuek Tan, Qiaoran Meng, Mei Lin Lock, Tri Cao, Shumin Deng, Nay Oo, Hoon Wei Lim, Bryan Hooi WWW 2025 (Demo Track) PhishIntel cite We present PhishIntel, an end-to-end phishing detection system for real-world deployment, with a fast-slow task system architecture that ensures low response latency while retaining the robust detection capabilities of RBPDs for zero-day phishing threats.
	PhishAgent: A Robust Multimodal Agent for Phishing Webpage Detection Tri Cao, Chengyu Huang, Yuexin Li, Huilin Wang, Amy He, Nay Oo, Bryan Hooi AAAI* 2025 (Oral) PhishAgent cite We introduce PhishAgent, a multimodal agent that combines a wide range of tools, integrating both online and offline knowledge bases with multimodal large language models, for phishing detection.
	KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection Yuexin Li, Chengyu Huang, Shumin Deng, Mei Lin Lock, Tri Cao, Nay Oo, Hoon Wei Lim, Bryan Hooi USENIX Security 2024 KnowPhish Video Webpage Spider cite We propose 1) KnowPhish, a large-scale multimodal brand knowledge base that can be integrated with any reference-based phishing detector (RBPD) in a plug-and-play manner, and 2) KnowPhish Detector (KPD), a multimodal RBPD to detect phishing webpages with or without logos.
	Prompt-Based Zero-and Few-Shot Node Classification: A Multimodal Approach Yuexin Li, Bryan Hooi ArXiv 2023 (Preliminary Work) cite TBD
	Spatial-Temporal Graph Neural Network Framework with Multi-source Local and Global Information Fusion for Traffic Flow Forecasting Yuexin Li, Jianyu Li, Zijia Wang, Zhihui Zhan CCF Conference on Computer Supported Cooperative Work and Social Computing (CCSCW) 2021 cite A generic spatial-temporal deep learning framework that mines spatial-temporal features locally and globally.
	Cloudde-based Distributed Differential Evolution for Solving Dynamic Optimization Problems Yuexin Li, Zhihui Zhan, Hu Jin, Jun Zhang International Conference on Intelligent Control and Information Processing (ICICIP) 2019 cite A message passing interface (MPI) based distributed multi-population differential evolution (DE) algorithm with adaptive migration strategy (AMS).

Honors

[2025/01] NUS Research Scholarship
[2020/06] Hongping Changqing Student Innovation Scholarship (RMB 2,000)
[2019/12] SCUT First-class Scholarship (RMB 4,000, Top 10%)
[2019/11] National 2nd Prize of Contemporary Undergraduate Mathematical Contest in Modeling (Top 3%).
[2018/12] SCUT First-class Scholarship (RMB 4,000, Top 10%)

Service

Journal Reviewer:

- IEEE Transactions on Information Forensics and Security (T-IFS)

Workshop Reviewer:

- ICLR 2025 Workshop on Reasoning and Planning for Large Language Models

This website is built on this source code.