Xuan Xie

Ph.D Student
University of Alberta

E-mail: xxie9[at]ualberta[dot]ca
[Google Scholar]
Study as if you were to live forever, live as if you were to die tomorrow

About

Education

2022-now: Ph.D. student, University of Alberta, Edmonton, Canada. Supervisor: Prof. Lei Ma

2019-2021: Master of Science, Max Planck Institute for Software Systems, Kaiserslautern, Germany. Supervisor: Prof. Daniel Neider and Prof. Maria Christakis

2015-2019: Bachelor in Software Engineering, Sun Yat-sen University, Guangzhou, China

Research Interests

Safety Analysis for Large Language Model (Safe LLM) [arxiv'23a, arxiv'24a]

Control, Testing, Monitoring, Repairing for AI-enabled Cyber-Physical Systems (AI-CPS) [arxiv'23b, ICSE'24, TSE'23, TCAD'22]

Neural Network Verification (NNV) to provide formal guarantees to AI models [AAAI'23, STTT'23, IJCAI'22, ATVA'21]

Publication

[pre-print] Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward
Xuan Xie, Jiayang Song, Zhehua Zhou, Yuheng Huang, Da Song, Lei Ma
Under submission

[pre-print] LUNA: A Model-Based Universal Analysis Framework for Large Language Models
Da Song*, Xuan Xie*, Jiayang Song, Derui Zhu, Yuheng Huang, Felix Juefei-Xu, Lei Ma
Under submission (equal contribution)

[pre-print] MOSAIC: Model-based Safety Analysis Framework for AI-enabled Cyber-Physical Systems
Xuan Xie, Jiayang Song, Zhehua Zhou, Fuyuan Zhang, Lei Ma
Under submission

[ICSE'24] Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation
Zhehua Zhou*, Jiayang Song*, Xuan Xie*, Zhan Shu, Lei Ma, Dikai Liu, Jianxiong Yin, Simon See
The 46th International Conference on Software Engineering, the Software Engineering in Practice track (CCF rank A, equal contribution)

[TSE'23] SIEGE: A Semantics-Guided Safety Enhancement Framework for AI-enabled Cyber-Physical Systems
Jiayang Song, Xuan Xie, Lei Ma
IEEE Transactions on Software Engineering. (CCF rank A)

[AAAI'23] DeepGemini: Verifying Dependency Fairness for Deep Neural Network
Xuan Xie, Fuyuan Zhang, Xinwen Hu, Lei Ma.
The Thirty-Seventh AAAI Conference on Artificial Intelligence, Special Track on Safe and Robust AI. (CCF rank A)

[STTT'23] Analysis of Recurrent Neural Networks via Property-directed Verification of Surrogate Models
Igor Khmelnitsky*, Daniel Neider*, Rajarshi Roy*, Xuan Xie*, Benoît Barbot, Benedikt Bollig, Alain Finkel, Serge Haddad, Martin Leucker and Lina Ye.
The International Journal on Software Tools for Technology Transfer (CCF rank C, equal contribution )

[TCAD'22] Online Reset for Signal Temporal Logic Monitoring
Zhenya Zhang, Paolo Arcaini, Xuan Xie
The IEEE Transaction on CAD of Integrated Circuits and Systems (CCF rank A)

[IJCAI'22] Neuro-Symbolic Verification of Deep Neural Networks
Xuan Xie, Kristian Kersting, Daniel Neider
The 31st International Joint Conference on Artificial Intelligence (CCF rank A)

[ATVA'21] “Property-Directed Verification and Robustness Certification of Recurrent Neural Networks
Igor Khmelnitsky*, Daniel Neider*, Rajarshi Roy*, Xuan Xie*, Benoît Barbot, Benedikt Bollig, Alain Finkel, Serge Haddad, Martin Leucker and Lina Ye
The 19th International Symposium on Automated Technology for Verification and Analysis (CCF rank C, equal contribution)

[ESEC/FSE'19] Exploring and Exploiting the Correlations between Bug-inducing and Bug-fixing Commits
Ming Wen, Rongxin Wu, Yepang Liu, Yongqiang Tian, Xuan Xie, Shing-Chi Cheung, Zhendong Su
The 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (CCF rank A)

[ICSE'19] Exposing Library API Misuses via Mutation Analysis
Ming Wen, Yepang Liu, Rongxin Wu, Xuan Xie, Shing-Chi Cheung, Zhendong Su.
The 41st International Conference on Software Engineering (CCF rank A)

Internship

Research Intern on Robotics Arm in Nvidia Omniverse Isaac Sim, Sycodal, Montreal, Canada, Jan 2023 – Mar 2023

Visiting Student, Southern University of Science and Technology, Shenzhen, China, December 2018 – August 2019, Supervisor: Prof. Yepang Liu and Prof. Ming Wen

Research Intern, The Hong Kong University of Science and Technology, Hong Kong, China, August 2018 – November 2018, Supervisor: Prof. Shing-Chi CHEUNG, Prof. Yepang Liu and Prof. Ming Wen

Talk

ICSE 2024: SIEGE: A Semantics-Guided Safety Enhancement Framework for AI-enabled Cyber-Physical Systems.

ICSE 2024: Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation.

AAAI 2023: DeepGemini: Verifying Dependency Fairness for Deep Neural Network.

IJCAI 2022: Neuro-Symbolic Verification of Deep Neural Networks.

ATVA 2021: Property-Directed Verification and Robustness Certification of Recurrent Neural Networks

HIGHLIGHT 2021: Property-Directed Verification and Robustness Certification of Recurrent Neural Networks

LWDA 2021: Property-Directed Verification and Robustness Certification of Recurrent Neural Networks

Service

Journal Reviewer

Conference Reviewer/PC member

Student Volunteer

Teaching

UAlberta 2024 Winter

UAlberta 2023 Fall