Rui Mei (梅瑞)

Rui Mei (梅瑞)

iFLYTEK

I am currently serving as a principal research fellow at the iFLYTEK Security Laboratory. I hold a Ph.D. in Cybersecurity and several international certifications, including CISSP, CCSP, CISA, and CDPSE. My research interests span cybersecurity, system security, and AI security, with a particular emphasis on building secure and trustworthy AI systems — especially LLMs — as well as exploring the applications of AI in cybersecurity and advancing system security technologies.

Throughout my career, I have led and contributed to a range of academic research projects and enterprise-driven initiatives in cyberspace and system security. My work has encompassed malware analysis, intrusion detection, secure software development, and vulnerability assessment. In recent years, my focus has shifted toward the security evaluation of large AI models, addressing challenges such as adversarial robustness, model alignment, and content compliance in AIGC.

🔥 News

  • 2025-03-25, Invited Talk: Artificial Intelligence Applications and Security Challenges of Large Language Models.
  • 2024-11-08, Our research paper focusing on toxicity labels aggregation for AIGC has been accepted by the CSAI 2024.

📖 Educations

  • 2017.09 - 2023.06, Ph.D. in Cyberspace Security, University of Chinese Academy of Sciences, China, supervised by Prof. Han-Bing Yan.
  • 2011.09 - 2014.06, M.Eng. in Software Engineering, Peking University, China, supervised by Prof. Weiping Wen.
  • 2003.09 - 2007.06, B.Sc. in Computer Science and Applications, Peking University, China, supervised by Assoc. Prof. Congyi Liu.

📝 Publications

2024

  1. Bingtao Chang, Weiping Wen, Xiaojie Wu, Siyang Cheng, Jianchun Jiang, and Rui Mei (Corresponding Author), TCLens: Towards Toxicity Tags Aggregation of Massive Labels Generated by Content Moderation for AIGC, Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence, pp. 466–473.

2022

  1. Qinqin Wang, Hanbing Yan, Chang Zhao, Rui Mei, Zhihui Han, and Yu Zhou, Measurement of Malware Family Classification on a Large-Scale Real-World Dataset, IEEE TrustCom 2022, pp. 1390–1397.
  2. Qinqin Wang, Hanbing Yan, Chang Zhao, Rui Mei, Zhihui Han, and Yu Zhou, APT Attribution for Malware Based on Time Series Shapelets, IEEE TrustCom 2022, pp. 769–777.
  3. Rui Mei, Han-Bing Yan, Yongqiang He, Qinqin Wang, Shengqiang Zhu, and Weiping Wen, Considerations on Evaluation of Practical Cloud Data Protection, in: Cyber Security: 19th China Annual Conference, CNCERT 2022, Springer, pp. 51–69.
  4. Rui Mei, Hanbing Yan, Qinqin Wang, Zhihui Han, and Zhuohang Lyu, TDLens: Toward an Empirical Evaluation of Provenance Graph-Based Approach to Cyber Threat Detection, China Communications, 19(10): 102–115.
  5. Yueqiang Cheng, Zhi Zhang, Yansong Gao, Zhaofeng Chen, Shengjian Guo, Qifei Zhang, Rui Mei, Surya Nepal, and Yang Xiang, Meltdown-type Attacks Are Still Feasible in the Wall of Kernel Page-Table Isolation, Computers & Security, 113: 102556.

2021

  1. Rui Mei, Han-Bing Yan, Zhi-Hui Han, and Jian-Chun Jiang, CTScopy: Hunting Cyber Threats within Enterprise via Provenance Graph-Based Analysis, IEEE QRS 2021, pp. 28–39.
  2. Rui Mei, Han-Bing Yan, and Zhi-Hui Han, Ransomlens: Understanding Ransomware via Causality Analysis on System Provenance Graph, in: Science of Cyber Security, SciSec 2021, Springer, pp. 252–267.
  3. Rui Mei, Han-Bing Yan, Yuan Shen, and Zhi-Hui Han, Application Research of Slicing Technology of Binary Executables in Malware Detection, Journal of Cyber Security, 6 (3), pp.125-140. (In Chinese)

2019

  1. Qinqin Wang, Hao Zhou, Han-Bing Yan, Rui Mei, and Zhi-Hui Han, Cyber Security Posture Analysis based on Spread Logs of Malware, Journal of Cyber Security, 4 (5), pp.14-24. (In Chinese)

2018

  1. Zhuo-Hang Lv, Han-Bing Yan, and Rui Mei, Automatic and Accurate Detection of Webshell Based on Convolutional Neural Network, in: Cyber Security: 15th International Annual Conference, CNCERT 2018, Springer, pp. 73–85.

🧑‍🏫 Professional Experience

  • 2023.07 - Present, Principal Research Fellow, iFLYTEK Security Laboratory, Hefei, China
  • 2017.09 - 2023.06, Research Intern, Institute of Information Engineering, CAS, Beijing, China
  • 2017.07 - 2022.08, Research Fellow, CNCERT/CC, Beijing, China
  • 2014.12 - 2017.07, Senior Engineer, iFLYTEK Co., Ltd., Hefei, China
  • 2012.09 - 2014.07, Research Assistant, Peking University, Beijing, China [Research Group]
  • 2007.10 – 2011.10, Engineer, ANH Branch, National Center for Statistics and Computing, Hefei, China

🧑‍💼 Professional Services

  • Appointed Distinguished Expert, ISC2 Chengdu Chapter (International Information Systems Security Certification Consortium)
  • Silver Member, ISACA Hong Kong Chapter (Information Systems Audit and Control Association)
  • Senior Member, China Computer Federation (CCF)
  • Council Member, Beijing Computer Federation (BCF)
  • Senior Lecturer, Network and Information Security Advanced Career Education (NSACE), Education and Examination Center of MIIT, China