Ruofan Liu’s Personal Website
Welcome to Liu Ruofan, 刘若凡’s homepage
My name is Liu Ruofan, I obtained my Bachelor’s degree at the National University of Singapore, Statistics. I am now a fourth-year CS Ph.D. candidate under the supervision of Prof. Dong Jin Song. My research interest is AI’s application in Web Security.
News
Selected Publications
| Title | Paper & Slides | Code | Video |
|---|---|---|---|
| Ruofan Liu, Yun Lin, Yifan Zhang, Penn Han Lee, and Jin Song Dong. Knowledge Expansion and Counterfactual Interaction for Reference-Based Phishing Detection. USENIX Security 2023 | Paper Slides | Dynaphish  MyXdriver  | Video  |
| Xiaoning Ren, Yun Lin, Yinxing Xue, Ruofan Liu, Jun Sun, Zhiyong Feng and Jin Song Dong. DeepArc: Modularizing Neural Networks for the Model Maintenance. ICSE 2023 | Paper | DeepArc  | -- |
| Ruofan Liu, Yun Lin, Xianglin Yang, Jin Song Dong. Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective. NeurIPS 2022 | Paper Poster | Influence4Metric  | Video |
| Xianglin Yang, Yun Lin, Ruofan Liu, Jin Song Dong. Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training. IJCAI 2022 | Paper | TimeVis  | Video |
| Ruofan Liu, Yun Lin, Xianglin Yang, Siang Hwee Ng, Dinil Mon Divakaran, Jin Song Dong. Inferring Phishing Intention via Webpage Appearance and Dynamics: A Deep Vision Based Approach. USENIX Security 2022 | Paper Slides | PhishIntention  | Video  |
| Xianglin Yang#, Yun Lin#, Ruofan Liu, Zhenfeng He, Chao Wang, Jin Song Dong, and Hong Mei. DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training. AAAI 2022 | Paper | DeepVisualInsight  | Video |
| Yun Lin#, Ruofan Liu#, Dinil Mon Divakaran, Jun Yang Ng, Qing Zhou Chan, Yiwen Lu, Yuxuan Si, Fan Zhang, Jin Song Dong. Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages. USENIX Security 2021 | Paper Slides | Phishpedia  | Video  |
Tools and Systems:
- Phishpedia: An explainable reference-based phishing detector based on brand intention
- PhishIntention: An explainable reference-based phishing detector phishing detector which considers both the brand intention and credential-taking intention
- Influence4Metric: An influence-function-based explanation and debugging tool for Deep Metric Learning Tasks
- DynaPhish: A complementary module for all reference-based phishing detectors with brand knowledge expansion and counterfactual interaction
- MyXDriver: A selenium-based webdriver that supports automatic form filling, form submission, and suspicious behavior inspection
Benchmark:
- Phishpedia 30K Phishing: The largest static benchmark for phishing identification, including URL, HTML, and screenshots.
- DynaPD 6K Phishing Kits: The largest interactable, safe collection of phishing kits.
Awards
- NUS SoC Research Achievement Award in 2021/2022 Sem 1
- Top 1 student in NUS Statistics Batch 2020
- Lijen Industrial Development Medal (Best Academic Exercise/Projects in the Discipline) in Academic Year 2019
- NTUC Medal in Academic Year 2019
- Saw Swee Hock Gold Medal in the Academic Year 2019
- SNAS Award 2020 (Singapore National Academy of Science)
Patent
- Yun Lin, Ruofan Liu, Dinil Mon Divakaran, Jun Yang Ng, and Jin Song Dong. Phishpedia: Towards an Approach of Phishing Identification with Visual Explanation. Provisional patent filed in Singapore (Trustwave, Singtel)
Service
Conference PC Membership
- Year of 2023. Program Committee (PC) for the 28th IEEE Pacific Rim International Symposium on Dependable Computing.
Contacts
- Email: liu.ruofan16[at]u[dot]nus[dot]edu
- GitHub page: https://github.com/lindsey98/
- Google Scholar: https://scholar.google.com/citations?user=g2M2UwsAAAAJ&hl=en