I obtained my Ph.D. from the University of Chinese Academy of Sciences under the supervision of Professor Jingguo Ge. During my Ph.D. studies, I primarily focused on network traffic identification and tracking. After graduation, I worked at Huawei, where I had the opportunity to participate in projects related to information retrieval, which sparked my interest in LLM-based Agents, natural language processing, and large language models (LLMs). I am currently employed at the Institute of Information Engineering, Chinese Academy of Sciences, where I mainly conduct research in the field of large models. To date, I have published more than 10 papers in areas such as deep learning and LLMs, and I have served as a session chair or reviewer for several international conferences, including IJCNN and CIKM.

My research fields involve:

  • Large Model Agents Collaboration
  • LLM performance and security evaluation
  • Natural Language Processing
  • Blockchain
  • Traffic Classification

🎓 Education

  • 2015.09 - 2019.06, University of Chinese Academy of Sciences, School of Cyber Security, Beijing China, Ph.D
  • 2012.09 - 2015.06, Capital Normal University, Computer Application Technology, Beijing China, Master Degree
  • 2008.09 - 2012.06, Shandong University of Science and Technology Computer Science and Technology, Shandong China, Bachelor Degree

📝 Publications

Accepted

  • Haozhe Li, Hanwen Kang, Zhongjiang Yao*, Yepeng Yao, Yingxiao Xiang, Zhengwei Jiang, Xiaodan Zhang. PrivacyShadow: Unveiling Privacy Vulnerabilities in VLMs through MIAs. The 33rd ACM International Conference on Multimedia (ACM MM 2025). (CCF A, Submitted)

  • Xuehai Tang, Xikang Yang, Zhongjiang Yao*, Jie Wen, Xi Zhou, Jizhong Han, Songlin Hu. Enhancing LLM Jailbreak: A Dual-Strategy Approach of Token Suppression and Induction. 43rd IEEE – International Performance Computing and Communications Conference (CSCWD 2025). (CCF C, Accepted)

Published

In English

  • Guoyi Li, Zhongjiang Yao†, Die Hu, Yingrui Xu, Xiaodan Zhang, Honglei Lyu. Emotion-aware Structural Enhancement Graph Auto-Encoder for Rumor Detection. 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025), (CCF-B) [网页][预览][下载]

  • Shang Shang, Zhongjiang Yao*, Xinqiang Zhao, Yepeng Yao, Yali Su, Zhijing Fan, Xiaodan Zhang, Zhengwei Jiang. Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent. The Computer Journal. (CCF B) [网页][预览][下载]

  • Xuehai Tang, Wenjie Xiao, Zhongjiang Yao*, Jizhong Han. SwordEcho: A LLM Jailbreaking Optimization Strategy Driven by Reinforcement Learning. The 2024 8th International Conference on Computer Science and Artificial Intelligence (CSAI 2024), (CCF-C) [网页][预览][下载]

  • Shangshang, Zhongjiang Yao*, Liya Su, Yepeng Yao, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang. IntentObfuscator: A jailbreaking method via confuses LLM with prompts. 29th European Symposium on Research in Computer Security (ESORICS 2024). (CCF B) [网页][预览][下载]

  • Xuehai Tang, Zhongjiang Yao*, Huazhen Zhong, Yuanshu Zhao, Guan Wang, Xiaodan Zhang, Jizhong Han. EthGAN: Improving Ethereum Account Classification Accurary via Data Augmentation. International Joint Conference on Neural Networks (IJCNN 2024). (CCF C) [网页][预览][下载]

  • Xuehai Tang, Zhongjiang Yao*, Jie Wen, Yangchen Dong, Jizhong Han, Songlin Hu. Reinforcement Learning-Powered Effectiveness and Effciency Few-Shot Jailbreaking Attack LLMs. *The 22nd IEEE International Symposium on Parallel and Distributed Processing with Applications (IEEE ISPA 2024). (CCF C) [网页][预览][下载]


JNCA 2020
sym
  • Zhongjiang Yao, Jingguo Ge Yulei Wu, Xiaosheng Lin, Runkang He, Yuxiang Ma. Encrypted traffic classification based on Gaussian mixture models and Hidden Markov Models. Journal of Network and Computer Applications (JNCA), 2020, Volume 166: 102711. (JCR:Q1; IF:8.7; CCF B)
    [网页] [预览] [下载]
JPDC 2019
sym
  • Zhongjiang Yao, Jingguo Ge, Yulei Wu, Linjie Jian. A privacy preserved and credible network protocol. Journal of Parallel and Distributed Computing (JPDC). 2019, , Volume 132: 150-159. (JCR:Q1; IF:3.8; CCF C)
    [网页] [预览] [下载]
ICC 2019
sym
  • Zhongjiang Yao, Lei Zhang, Jingguo Ge, Yulei Wu, Xiaodan Zhang. An Invisible Flow Watermarking for Traffic Tracking: A Hidden Markov Model Approach. the 53rd IEEE International Conference on Communications (ICC). 2019, 64(1–4): 493–500. (Flagship Conference, CCF C)
    [网页] [预览] [下载]
  • Tengyu Liu, Jingguo Ge, Yulei Wu, Bowei Dai, Liangxiong Li, Zhongjiang Yao, Jifei Wen, Hongbin Shi. A New Bitcoin Address Association Method Using a Two-Level Learner Model. The 19th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP). 2019, Volume 11945: 349-364. (CCF C)
    [网页] [预览] [下载]

  • Zhuang Zou, Jingguo Ge, Hongbo Zheng, Yulei Wu, Chunjing Han, Zhongjiang Yao. Encrypted Traffic Classification with a Convolutional Long Short-Term Memory Neural Network. 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). 2018: 329-334. (CCF C)
    [网页] [预览] [下载]

  • Zhongjiang Yao, Jingguo Ge, Yulei Wu, Xiaodan Zhang, Qiang Li, Lei Zhang, Zhuang Zou. Meek-Based Tor Traffic Identification with Hidden Markov Model. 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). 2018:2736. (CCF C)
    [网页] [预览] [下载]

  • Zhongjiang Yao, Xiaodan Zhang, Yuepeng E, Tong Li, Jingguo Ge, Haina Tang. Performance Evaluation and Analysis of the Virtual Networks Built by Different Virtual Machine Managers. 2016 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), 2016: 39. (HPCC C)
    [网页] [预览] [下载]

  • Tong Li, Xiaodan Zhang, Zongzhen Liu, Jingguo Ge, Zhongjiang Yao, Yuepeng E, Yulei Wu, Lei Zhang. Performance Investigation and Comparison between Virtual Networks and Physical Networks Based on an Advanced Testbed Network. 15th IEEE International Conference on Computer and Information Technology; 14th IEEE International Conference on Ubiquitous Computing and Communications; 13th IEEE International Conference on Dependable, Autonomic and Secure Computing; 13th IEEE International Conference on Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICom). 2015: 1216-1221.
    [网页] [预览] [下载]

  • Meng Li, Quanliang Jing, Zhongjiang Yao, Jingang Liu. On the Prevention of Invalid Route Injection Attack. Intelligent Information Processing (IIP). 2014: 294-302.
    [网页] [预览] [下载]

In Chinese


  • Shixiong Jin, Xiaodan Zhang, Jingguo Ge, Hongbin Shi, Yi Sun, Ming Li, Yeming Lin,Zhongjiang Yao.Overview of blockchain consensus algorithm.Journal of Cyber Security.2021,6(2):85-100 (in Chinese). (CCF )
    [网页] [预览] [下载]

  • Zhongjiang Yao, Jingguo Ge, Xiaodan Zhang, Hongbo Zheng, Zhuang Zou, Kunkun Sun, Zihao Xu. Research Review on Traffic Obfuscation and Its Corresponding Identification and Tracking Technologies. Journal of Software, 2018, 29(10): 3205-3222 (in Chinese). (CCF )
    [网页] [预览] [下载]

  • Zhongjiang Yao, Jingguo Ge. A Summary of the Theory and Application of BlockChain. e-Science Technology & Application. 2017,8(2):3-17 (in Chinese). (CCF)
    [网页] [预览] [下载]

  • Zhongjiang Yao, Jinggang Liu, Quanliang Jing, Meng Li, Jingping Bi. DESIGN AND IMPLEMENTATION OF IS-IS NETWORK-ORIENTED NETMONITOR SYSTEM. Computer Applications and Software. 2015,32(9):112-115160 (in Chinese). (CSCD)
    [网页] [预览] [下载]

🔖 Patents


  • Zhongjiang Yao, Xuehai Tang, Wenjie Xiao, Xiaodan Zhang, Jizhong Han, Songlin Hu. An Ethereum account identity identification method and system based on data enhancement. CN: 202311521280.6, 2023-11-15.
  • Zhongjiang Yao, Xuehai Tang, Guan Wang, Xiaodan Zhang, Jizhong Han, Songlin Hu. A Bitcoin abnormal account identification method and system based on community information. CN: 202311695328.5, 2023-12-11.
  • Quanliang Jing, Lin Liu, Jingping Bi, Zhongjiang Yao. A method and system for link anomaly detection in IS-IS networks. CN: CN107222359B, 2020-01-07. [网页]
  • Quanliang Jing, Lin Liu, Jingping Bi, Zhongjiang Yao. A link anomaly detection method, system, device and chip in an is‑is network.[网页]

🏅 Awards

  • 2021.Spring Innovation Competition, Huawei Central Software Research Institute Bronze Award
  • 2016, 2017, 2018 Outstanding Doctoral Award of the Director of IIE, CAS
  • 2016.October Participate in the Beijing Half Marathon, Athlete Memorial Award

🏛️ Academic Activities

  • 2024.08, Reviewer for CCF-B conference 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024)
  • 2019.06, Participate in the ICC-2019, Poster presente, Shanghai, China
  • 2016.12, Participate in the HPCC-2016, Oral presenter, Sydney, Austrilia

💻 Work Experience

  • *2021.12 - Now, Institute of Information Sciences, Chinese Academy of Sciences, Beijing, China
  • *2019.07 - 2021.12, Beijing Huawei Digital Technologies Co., Ltd., Beijing, China