USI - Email

Archive / INF Seminars / INF_2025_11_07_JamesZheng

USI - Email

	From Probabilistic Testing to Certifiable AI: Large Language Models and Neuro Symbolic Reasoning for Verifiable Autonomous Systems

Host: Prof. Paolo Tonella

Friday

11.07

USI Campus EST, Room D1.15

11:00 - 12:00


	James Zheng Macquarie University

Abstract: Learning-enabled Cyber-Physical Systems (LE-CPS), such as autonomous vehicles and drones, face critical safety and reliability challenges due to the stochastic nature of deep neural networks. In our FSE’22 and TSE’23 studies, we conducted an in-depth investigation into industry testing practices, uncovering significant gaps between current testing techniques and the needs for regulatory assurance. To address these challenges, we introduced two pioneering approaches: test reduction for ROS-based multi-module autonomous driving systems, and scenario-based construction for checking traffic rule compliance in autonomous driving systems.
This talk will then present our recent progress in bridging probabilistic testing with formal reasoning. I will first cover our FSE’24 work on reviving model-based testing with Large Language Models (LLMs), followed by TSE’24 and ICSE’25 efforts on LLM-driven scenario generation and online testing for uncrewed drone autolanding. Finally, I will introduce our FSE’25 paper NeuroStrata, which leads a neurosymbolic shift from black-box machine learning to white-box, human-understandable reasoning, aiming to improve interpretability, testability, and certification of AI components in safety-critical CPS.

Biography: Prof. Xi Zheng is an Associate Professor at Macquarie University and an ARC Future Fellow (2024). He leads the Intelligent Systems Research Group (ITSEG.ORG) and serves as Director of International Engagement and Deputy Program Leader in Software Engineering. His research focuses on cyber-physical systems, safety analysis, distributed learning, and trustworthy AI. He has secured over $2.4 million in funding and received awards including the Deakin Industry Researcher Award and MQ ECR Award. Prof. Zheng has held visiting roles at UCLA and UT Austin, and serves on editorial boards and program committees for leading conferences and journals in software and systems engineering.