I am currently a postdoctoral researcher at the School of Cyberspace Security, Huazhong University of Science and Technology (HUST), working under the joint supervision of Prof. Deqing Zou and Prof. Haoyu Wang. I received my Ph.D. in Cyberspace Security from the School of Cyberspace Security, Beijing University of Posts and Telecommunications (BUPT) in June 2025, where I was advised by Prof. Guo’ai Xu. My research interests primarily focus on leveraging AI technologies to address security and privacy issues in software engineering. During my PhD, I have published 3 CCF A papers, which improve Android malware detection by utilizing DNN uncertainty at the data layer (MalCleanse), model training layer (MalTutor), and inference layer (MalCertain). Currently, I am exploring the security challenges of LLMs and how LLMs can be applied to solve security problems.

Education

Publications

Uncertainty + Android Malware Detection

• MalCertain: Enhancing Deep Neural Network Based Android Malware Detection by Tackling Prediction Uncertainty.
  Haodong Li, Guosheng Xu_(&), Liu Wang, Xusheng Xiao, Xiapu Luo, Guoai Xu, and Haoyu Wang_(&).
  ICSE 2024. MalCertain
• Mitigating Emergent Malware Label Noise in DNN-Based Android Malware Detection.
  Haodong Li_(*), Xiao Cheng_(*), Guohan Zhang_(&), Guosheng Xu, Guoai Xu, and Haoyu Wang_(&).
  FSE 2025 MalCleanse
• Understanding Model Weaknesses: A Path to Strengthening DNN-Based Android Malware Detection.
  Haodong Li, Xiao Cheng _(&), Yanjie Zhao, Guosheng Xu, Guoai Xu, and Haoyu Wang_(&).
  ISSTA 2025 MalTutor
• Towards Improved DNN-Based Android Malware Detection via Uncertainty Estimation.
  Haodong Li,Xiao Cheng _(&), Liu Wang, and Haoyu Wang_(&).
  TOSEM 2026

LLM + Security and Privacy

• Digger: Detecting Copyright Content Mis-usage in Large Language Model Training.
  Haodong Li, Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu, Guoai Xu, Guosheng Xu, Haoyu Wang.
  arXiv 2024 Digger

• As If We’ve Met Before: LLMs Exhibit Certainty in Recognizing Seen Files.
  Haodong Li, Jingqi Zhang, Cheng Xiao, Peihua Mai, Haoyu Wang, Yan Pang.
  arXiv 2025 CopyCheck

• Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis.
  Hongzhou Rao, Zikan Dong, Yanjie Zhao, Haodong Li, Haoyu Wang.
  ICSE 2026

Honors & Awards

• [2024] First Class Academic Scholarship for PhD Students, BUPT
• [2025] Outstanding Doctoral Dissertation Award of BUPT

Services

• PC Member (Artifact Evaluation Track), IEEE S&P 2025.
• PC Member (Artifact Evaluation Track), IEEE ISSRE 2025.
• Reviewer for ACM Transactions on Software Engineering and Methodology (TOSEM), 2025
• PC Member (Artifact Evaluation Track), IEEE S&P 2026.