About Me

I am currently a third-year PhD candidate at Shanghai Jiao Tong University, supervised by Dr. Xi Lin. Currently, I am also a research intern at Shanghai AI Laboratory, mentored by Dr. Dongrui Liu. I received my bachelor’s degree of information security from School of Electronic Information and Electrical Engineering at Shanghai Jiao Tong University in 2022, supervised by Dr. Kui Meng. My research interests include graph neural networks, agent safety & security, recursive self-improvement, and trustworthy AI. If you are interested in my research or have any questions, please feel free to contact me.

🔥 News

• 2026.07:  🎉🎉 Our work “Towards Domain Generalized Neural Architecture Search via Language-Guided Visual Augmentation” has been ACCEPTED for publication in ACM Multimedia 2026 (Main Track).
• 2026.06:  🎉🎉 Our work “GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning” has been ACCEPTED for publication in IEEE Transactions on Dependable and Secure Computing (TDSC).
• 2026.05:  🚀 We released the technical report for “AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security”. Great Honor to work with colleagues from Shanghai AI Lab!
• 2026.04:  🎉🎉 Our work “Is There a Structural Privacy Risk in Graph Prompting with LLMs?” has been ACCEPTED for publication in International Conference on Database Systems for Advanced Applications (DASFAA 2026).
• 2025.11:  🎉🎉 Our work “Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images” has been ACCEPTED for publication in npj Digital Medicine.
• 2025.01:  🎉🎉 Our work “FeCoGraph: Label-aware Federated Graph Contrastive Learning for Few-shot Network Intrusion Detection” has been ACCEPTED for publication as a REGULAR paper in IEEE Transactions on Information Forensics & Security.

  📝 Publications

📄 Conference & Journal Papers

• ACM MM 2026 Towards Domain Generalized Neural Architecture Search via Language-Guided Visual Augmentation
  Qinghua Mao, Xi Lin, Zhongze Wu, Jun Wu, Xiangrui Cai, Xiu Su
  ACM Multimedia 2026 (Main Track)

• IEEE TDSC GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning
  Jiani Zhu, Xi Lin, Yuxin Qi, Qinghua Mao, Jun Wu
  IEEE Transactions on Dependable and Secure Computing (TDSC), 2026

• DASFAA 2026 Is There a Structural Privacy Risk in Graph Prompting with LLMs?
  Jiani Zhu, Xi Lin, Yuxin Qi, Qinghua Mao, Jianhua Li, Jun Wu
  International Conference on Database Systems for Advanced Applications (DASFAA 2026)

• npj Digit. Med. Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images
  Xiu Su, Qinghua Mao, Zhongze Wu, Xi Lin, Shan You, Yue Liao, Chang Xu
  npj Digital Medicine, 2025

• IEEE TIFS FeCoGraph: Label-aware Federated Graph Contrastive Learning for Few-shot Network Intrusion Detection
  Qinghua Mao, Xi Lin, Wenchao Xu, Yuxin Qi, Xiu Su, Gaolei Li, Jianhua Li
  IEEE Transactions on Information Forensics & Security (TIFS), 2025

• ICASSP 2024 Prompting Label Efficiency in Federated Graph Learning Via Personalized Semi-Supervision
  Qinghua Mao, Xi Lin, Xiu Su, Gaolei Li, Lixing Chen, Jianhua Li
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)

• IEEE ISPA 2023 Ensuring Minority Group Rights in Social IoT with Fairness-aware Federated Graph Node Classification
  Qinghua Mao, Xi Lin, Gaolei Li, Lixing Chen, Yuchen Liu, Yuxin Qi, Jianhua Li
  IEEE ISPA/BDCloud/SocialCom/SustainCom 2023

• IEEE MSN 2023 Multi-Level ACE-based IoT Knowledge Sharing for Personalized Privacy-Preserving Federated Learning
  Jing Wang, Xi Lin, Jun Wu, Qinghua Mao, Bei Pei, Jianhua Li, Suchang Guo, Baitao Zhang
  IEEE MSN 2023

📑 Preprints & Working Papers

• Before Agent Tells The Lie: Has Deception Already Been Represented?
  Xinling Li, Dadi Guo, Qingyu Liu, Qinghua Mao, Yi R Fung, Na Zou, Xia Hu, Dongrui Liu
  arXiv preprint arXiv:2610.06576, 2026

• SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
  Qinghua Mao, Wanying Qu, Dadi Guo, Leitao Yuan, Qingyu Liu, Yu Li, Guanxu Chen, Yanwei Fu, Xi Lin, Xia Hu, Dongrui Liu
  arXiv preprint arXiv:2609.02786, 2026

• SHE: Trajectory-Driven Safety Harness Evolution for LLM Agents
  Wanying Qu, Qinghua Mao, Yu Li, Jiyao Liu, Xin Zhang, Dadi Guo, Yanxu Zhu, Qingyu Liu, Leitao Yuan, Xi Lin, Shanfeng Zhu, Yanwei Fu, Jing Shao, Xia Hu, Dongrui Liu
  arXiv preprint arXiv:2608.09885, 2026

• AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
  Dongrui Liu, Yu Li, Zhonghao Yang, Peng Wang, Guanxu Chen, Yuejin Xie, Qinghua Mao, Wanying Qu, Yanxu Zhu, Tianyi Zhou, et al.
  Technical Report / arXiv preprint arXiv:2605.29801, 2026 [Project]

• Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
  Leitao Yuan, Qinghua Mao, Daizong Liu, Kun Wang, Wenjie Wang, Yan Teng, Jing Shao, Dongrui Liu
  arXiv preprint arXiv:2605.21541, 2026

• Towards Multi-Task Generative-AI Edge Services with an Attention-based Diffusion DRL Approach
  Yaju Liu, Xi Lin, Siyuan Li, Gaolei Li, Qinghua Mao, Jianhua Li
  arXiv preprint arXiv:2405.08328, 2024

• Improving Chinese Named Entity Recognition by Search Engine Augmentation
  Qinghua Mao, Jiatong Li, Kui Meng
  arXiv preprint arXiv:2210.12662, 2022

📖 Educations

• 2022.09 - 2028.03 (expected), Ph.D. in Computer Science and Cybersecurity, Shanghai Jiao Tong University.
• 2018.09 - 2022.06, B.Eng. in Information Security, Shanghai Jiao Tong University.

💼 Internships

• 2026.02 - Present, Research Intern, Shanghai AI Laboratory, Shanghai.

🎖 Honors and Awards

• 2024.09 Advanced Individual in Social Practice of SJTU
• 2022.09 1st-Class Academic Scholarship for Graduate Students (2022 - 2025)
• 2022.06 Outstanding Graduate of Shanghai Jiao Tong University
• 2021.08 3rd-Class Prize of National College Student Information Security Competition

💻 Service

• Reviewer: ICLR 2025/2026, ICCV 2025, AAAI 2026