Xin Chen

Xin Chen is an Assistant Professor in the Department of Computer Science at the University of New Mexico, where he conducts research at the intersection of cyber-physical systems, formal methods, and machine learning. His work focuses on safety and security verification for learning-enabled systems.

Research Interests:

• Safety and security of Cyber-Physical Systems (CPS) with machine learning components
• Formal verification and reachability analysis of hybrid and neural network-controlled systems
• Real-time monitoring and attack recovery in CPS
• Development of verification tools for safety-critical autonomous systems

Publication Trends: His recent publications (2020–2025) emphasize formal methods for neural network verification, attack recovery in CPS, and reachability analysis. Key themes include the use of polynomial arithmetic, linear approximations, and abstraction techniques to ensure safety in systems using deep learning and reinforcement learning.

Scientific Service:

• Program Committee Member: DAC 2025, VMCAI 2025, RTSS, AAAI, CAV, HSCC, ARCH, and others

Grants and Advising: Dr. Chen is the Principal Investigator (PI) on multiple grants, including an NSF-funded project on safety-directed abstraction and correction of learning-enabled CPS. While no formal students are listed, he collaborates extensively with researchers and students on funded projects and tool development. He leads research in formal verification and has mentored work on tools like Flow* and POLAR.

Labs and Tools:

• Flow*: A tool for reachability analysis and safety verification of nonlinear hybrid systems, with a reengineered high-performance version available on GitHub.
• POLAR: A framework for formal verification of neural network-controlled systems.