Yuan Xiao
Trustworthy AI · Verification · Security

Yuan Xiao

I am currently a Ph.D. student at the Software Institute, Nanjing University, under the supervision of Professor Zhenyu Chen and Associate Professor Chunrong Fang, with academic collaboration and guidance from Assistant Professor Shiqing Ma at the University of Massachusetts Amherst. I was also a joint Ph.D. student at the School of Computing, National University of Singapore, from November 2024 to November 2025, under the supervision of Professor Jinsong Dong, with collaboration and guidance from Professor Jun Sun. I received my bachelor's degree in Mathematics from Sun Yat-sen University in 2021, advised by Professor Xianping Guo.

Nanjing University Software Security Neural Verification Postdoc 2026
View Publications Open CV Email Me
Research

Current focus

Neural Network Verification

Certified robustness for deep neural networks, especially MaxPool-based architectures and tighter linear approximation methods.

Code Dataset Watermarking

Embedding, detecting, removing, and stress-testing watermarks in code datasets and neural code models.

AI Security

Backdoors, unauthorized model usage, and trustworthy deployment problems around modern learning systems.

Education

Academic background

2021 - 2026

Ph.D., Software Institute, Nanjing University.

Nov 2024 - Nov 2025

Joint Ph.D., School of Computing, National University of Singapore.

2017 - 2021

B.S. in Mathematics, Sun Yat-sen University.

Publications

Selected papers across verification, watermarking, and security

† co-first authors. * corresponding authors. For Findings of ACL, the CCF list does not count it as a regular ranked conference, so it is marked as N/A.

Watermarking for Code Large Language Models and Datasets

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Yuan Xiao†, Yuchen Chen†, Jiaming Wang, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang*, Jin Song Dong, Zhenyu Chen*

Findings of the Association for Computational Linguistics, 2026

CCF N/A CORE N/A

DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design

Yuchen Chen†, Yuan Xiao†, Chunrong Fang*, Zhenyu Chen*, Baowen Xu*

ESEC/FSE, 2026

CCF A CORE A*

PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models

Haocheng Huang, Yuchen Chen, Weisong Sun, Peizhuo Lv, Yuan Xiao, Chunrong Fang, Yang Liu, Xiaofang Zhang*

ESEC/FSE, 2026

CCF A CORE A*

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction

Yuan Xiao, Yuchen Chen, Shiqing Ma, Haocheng Huang, Chunrong Fang*, Yanwei Chen, Weisong Sun, Yunfeng Zhu, Xiaofang Zhang, Zhenyu Chen*

ISSTA, 2025 · Trondheim, Norway

CCF A CORE A
Paper Code

Robustness Verification for Neural Network

Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone

Yuan Xiao, Yuchen Chen, Shiqing Ma, Chunrong Fang*, Tongtong Bai, Mingzheng Gu, Yuxin Cheng, Yanwei Chen, Zhenyu Chen*

CVPR, 2025 · Tennessee, US

CCF A CORE A*
Paper Code

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

Yuan Xiao, Shiqing Ma, Juan Zhai, Chunrong Fang*, Jinyuan Jia, Zhenyu Chen*

CVPR, 2024 · Seattle, US

CCF A CORE A*
Paper Slides Code

Backdoor Research for Neural Network

Eliminating Backdoors in Neural Code Models for Secure Code Understanding

Weisong Sun, Yuchen Chen, Chunrong Fang*, Yebo Feng, Yuan Xiao, An Guo, Quanjun Zhang, Zhenyu Chen*, Baowen Xu, Yang Liu

FSE, 2025 · Norway

CCF A CORE A*
Paper Code

Robustness Testing for Neural Network

CooTest: An Automated Testing Approach for V2X Communication Systems

An Guo, Xinyu Gao, Zhenyu Chen*, Yuan Xiao, Jiakai Liu, Xiuting Ge, Weisong Sun, Chunrong Fang*

ISSTA, 2024 · Vienna, Austria

CCF A CORE A
Paper Code
Talks

Recent presentations

Talks and posters

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
Oral Presentation · ISSTA 2025 · June 2025 · Trondheim, Norway
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
Poster · Seattle Convention Center · June 2024 · Seattle, US

Highlights

Poster presentation at CVPR, plus an active publication pipeline across top AI and software engineering venues.

Service
Reviewer: AAAI 2023, NeurIPS 2024/2025/2026, ICLR 2025/2026, ICML 2025, TSE 2026.
External Review
TASE 2025, AAAI 2025, USENIX 2026, CVPR 2026.
Teaching

Teaching and academic activity

Teaching

Foundation of Data Science
Teaching Assistant, Undergraduate course · Nanjing University, Software Institute · Nanjing, Jiangsu

Awards and projects

Awards
Huawei Scholarship (2025), Model Graduate Student (2025), Nanjing University Graduate Scholarship (2021-2025), Outstanding Graduate Student (2022).
Projects
Safety-critical software quality assurance, Internet of Vehicles load analysis, and population measurement projects.
Contact

Open to postdoc and collaboration opportunities

If you are working on trustworthy AI, neural verification, or security for learning systems, feel free to reach out by email or check my Google Scholar profile.

yuan.xiao@smail.nju.edu.cn Google Scholar