Homepage redesigned around autonomous cyber agents, wireless body area networks, and reliable scientific computing.
About
I am a postdoctoral researcher at Zhejiang Lab, working across cyber security, wireless systems, and learning-based control. My research has moved from resource allocation and channel prediction in wireless body area networks toward autonomous security agents that can operate in uncertain, changing environments.
Beyond my main work on penetration testing and networked systems, I collaborate on reliable scientific computing, especially numerical precision and error compensation in large-scale simulation models.
News
Behaviour-diverse automatic penetration testing paper published in Frontiers of Computer Science.
New collaborations on numerical reliability for scientific computing models.
Selected Publications
Full publication list2025
2023
SetTron: Towards Better Generalisation in Penetration Testing with Reinforcement Learning
IEEE GLOBECOM 2023, pp. 4662-4667
2020
Power Control for Body Area Networks: Accurate Channel Prediction by Lightweight Deep Learning
IEEE Internet of Things Journal, 8(5), pp. 3567-3575
2025
Enhancing Single Precision with Quasi-Double Precision: Achieving Double-Precision Accuracy in MPAS-A Version 8.2.1
Geoscientific Model Development, 18(4), pp. 1089-1102
Selected Projects
05/2020
Wireless Channel Prediction via Deep Learning
Learning temporal channel behavior for transmit power control and adaptive resource allocation in wireless body area networks.
Read project details
06/2022 - Developing
Deep Reinforcement Learning Enabled Autonomous Penetration Testing
Reinforcement learning agents that explore attack paths, diversify behavior, and improve generalization across network security scenarios.
Read project detailsBlog & Notes
I plan to use this space for research notes, reading reflections, technical thoughts, and occasional personal writing that does not need to be as formal as a publication or project page.
Possible topics include autonomous penetration testing, reinforcement learning generalization, wireless channel prediction, research workflow, and lessons from doctoral/postdoctoral work.