Zonglei Jing

I'm a PhD student in Computer Science at Beihang University (BUAA) currently working on text-to-image generation security and control theory. My research focuses on developing defenses against adversarial attacks on AI systems, particularly in the context of generative models.

I work at the intersection of AI security and control theory, exploring how cognitive science principles can be applied to understand and mitigate vulnerabilities in generative AI systems. My recent work includes developing CogMorph, a framework for analyzing cognitive morphing attacks against text-to-image models, and studying optimal control strategies for hierarchical decision problems.

I've previously done research on reinforcement learning and game theory applications, particularly focused on leader-follower dynamics and Stackelberg games. I collaborate closely with researchers at BUAA working on multi-agent systems and robust control. My work aims to make AI systems more secure and reliable while maintaining their creative capabilities.

Publications

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

Zonglei Jing, Zonghao Ying, Le Wang, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao

Optimal Control and Filtering for Hierarchical Decision Problems With $H_\infty$ Constraint Based on Stackelberg Strategy

Optimal Control and Filtering for Hierarchical Decision Problems With $H_\infty$ Constraint Based on Stackelberg Strategy

Zonglei Jing, Xiaoqian Li, P. Ju, Huanshui Zhang

IEEE Transactions on Automatic Control 2024

Can Tricks Affect Robustness of Multi-Agent Reinforcement Learning?

Can Tricks Affect Robustness of Multi-Agent Reinforcement Learning?

Xiaoqian Li, P. Ju, Zonglei Jing

Cybersecurity and Cyberforensics Conference 2024

Leader-Follower Based Online Reinforcement Learning Algorithm in Problem with Hierarchy Decision Makers

Zonglei Jing, P. Ju, Xiaoqian Li

International Journal of Intelligent Control and Systems 2024

Optimal Trajectory Tracking for Unknown H∞ Constrained Systems Based on Reinforcement Learning

Optimal Trajectory Tracking for Unknown H∞ Constrained Systems Based on Reinforcement Learning

Xiaoqian Li, Zonglei Jing, P. Ju, Shufen Zhao

ACM Cloud and Autonomic Computing Conference 2023

Online Stackelberg learning solution for non-zero-sum games with infinite horizon cost*

Online Stackelberg learning solution for non-zero-sum games with infinite horizon cost*

Zonglei Jing, Xiaoqian Li, Xianglong Li, P. Ju, Tongxing Li, Shufen Zhao

ACM Cloud and Autonomic Computing Conference 2022

Incentive Stackelberg game for H∞$H_\infty$‐constrained multi‐hierarchy systems under observation information

Xiaoqian Li, Mengyu Bai, Huanshui Zhang, Zonglei Jing, P. Ju, Zhongjin Guo

IET Control Theory & Applications 2022

$H_{\infty}$ constrained control for multi-hierarchies decision players with asymmetric information

$H_{\infty}$ constrained control for multi-hierarchies decision players with asymmetric information

Liu Tang, Mengyu Bai, Xiaoqian Li, Zonglei Jing, Zhongjin Guo, P. Ju

Cybersecurity and Cyberforensics Conference 2022

Incentive game approach to $H_{\infty}$ -constrained system with hierarchy decision makers

Zonglei Jing, Xiaoqian Li, P. Ju, Jianzhong Zhang

Cybersecurity and Cyberforensics Conference 2022

Solution of Delayed Mixed H2/H∞ Problem with Continuous-time System based on Nash Game Approach

Xiaoqian Li, P. Ju, Zonglei Jing

Cybersecurity and Cyberforensics Conference 2021

A Nash Game Approach to Mixed H2/ H∞ Problem with Input Delay: The Discrete-time Case

Xiaoqian Li, P. Ju, Zhongjin Guo, Jing Lei, Zonglei Jing

Chinese Control and Decision Conference 2021