Dr. Fanxin Kong

Interests: Cyber-Physical Systems.

Techniques: machine learning, formal methods, control, optimization and algorithm design,

Applications: Autonomous systems including autonomous vehicles, drones, robotic arms and dogs.

Email: fkong at nd dot edu

Other profiles: Google Scholar, dblp Entry 

Dr. Fanxin Kong is a tenure-track assistant professor in the Department of Computer Science and Engineering at University of Notre Dame. Before that, he worked as a tenure-track assistant professor at Syracuse University and as a postdoctoral researcher with Prof. Insup Lee in the PRECISE Center at University of Pennsylvania. He obtained his Ph.D. in Computer Science at McGill University advised by Prof. Xue Liu. He is serving as the Information Director of ACM SIGBED.

I am looking for self-motivated PhD students. Interns, visiting students and scholars are all welcome. If you are interested in my research and working with me, please directly contact me with your CV.  

[Oct. 2024] Competition: Our SafePilot tool for assuring LLM-Enabled CPS has won the championship of Embedded System Software Competition (ESSC) at ESWEEK'2024! Big congratulations to Weizhe and Mengyu!

[Oct. 2024] Competition: My PhD student, Mengyu Liu, has won the championship of ACM SIGBED Student Research Competition (SRC) 2024! Big congratulations to Mengyu!

[Sep. 2024], Service: I will serve as a TPC member in RTAS 2025. Please consider to submit your best work!

[Sep. 2024], Paper: our paper "Pinpointing Actuator Attacks: A Novel Diagnostic Framework for Cyber-Physical Systems", has been accepted by the 3rd International Conference on Assured Autonomy (ICAA) 2024. Congratulations to Zifan!

[July 2024], Paper: our paper "Deadline-Safe Reach-Avoid Control Synthesis for Cyber-Physical Systems with Reinforcement Learning", has been accepted by the 45th IEEE Real-Time Systems Symposium (RTSS) 2024. Congratulations to Mengyu and all!

[July 2024], Service: I will serve as a TPC member in ICAA 2024.

[July 2024], Paper: our paper "Backdoor Attacks on Safe Reinforcement Learning-Enabled Cyber-Physical Systems", has been accepted by the ACM SIGBED International Conference on Embedded Software (EMSOFT), part of  Embedded Systems Week (ESWEEK) 2024. Congratulations to Shixiong and all!

[July 2024], Paper: our paper "Model-free PAC Time-Optimal Control Synthesis with Reinforcement Learning", has been accepted by the 22nd International Symposium on Formal Methods and Models for System Design (MEMOCODE), colocate with Embedded Systems Week (ESWEEK) 2024. Congratulations to Mengyu and all!

[June 2024], Paper: our paper "CPSim: Simulation Toolbox for Security Problems in Cyber-Physical Systems", has been accepted by the ACM Transactions on Design Automation of Electronic Systems (TODAES). Congratulations to Mengyu and all! Visit our CPSim page!

Secure & Safe Reinforcement Learning in CPS:

LLM-Enabled CPS:

Timing-Safe Learning Enabled CPS:

CPS Attack Recovery:

CPS Attack Detection & Diagnosis: 

Vunlnerability analysis for safe reinforcement learning in CPS 

    

No recovery vs real-time attack recovery, SVL  simulator

    

No recovery vs real-time attack recovery, indoor autonomous vehicles

    

Drone path recovery