Yifan Liao (廖一凡)

I'm the research assistant at NUS Research Institute in Chongqing, where I am supervised by Prof. Zhiyong Huang.

I obtained my M.Comp. in Artificial Intelligence at National University of Singapore (NUS), where I worked closely with Asso. Prof. Yun Lin and Prof. Jinsong Dong on my master dissertation project. Before Joining NUS, I received my B.Eng. in Mechanical Engineering at Chongqing University (CQU) in 2021

Email  /  CV  /  Scholar  /  Github /  linkedin

profile photo

Leading Research

I'm interested in AI4testing and Autonomous Driving testing. Most of my research is about detecting the anomalies targeting agents. Some projects are highlighted.

Detecting and Explaining Anomalies Caused by Web Tamper Attacks via Building Consistency-based Normality
Yifan Liao#, Ming Xu#, Yun Lin*, Xiwen Teoh, Xiaofei Xie, Hongyu Zhang, Jinsong Dong
ASE'24 (CCF-A)
Project Page | Paper | Code

This project aims to detect and explain attack-induced anomalies in web applications by learning normal behavioral during runtime. We model the normal constraints with first-order logic, and generate executable Python scripts. By leveraging LLMs in the learning process, this approach enhances both the detection and explanation of anomalies.

An Explanation-driven and Diversity-enhancing Approach for Boosting the Fuzzers of Autonomous Driving System
Yifan Liao, Yun Lin*, Xiaofei Xie, Jinsong Dong
arxiv, 2024
Project Page / Paper(TBD)

This project addresses the need for a diversity-driven and explanation-oriented solution by introducing DivX, which enhances existing ADS fuzzers. It achieves this by discovering diversified failures across different driving scenarios and deriving actionable explanations. These explanations help summarize failure patterns, generate test cases, and provide runtime remedies to avoid potential accidents.