城大首頁

徐衡 助理教授


徐衡 博士

助理教授 碩導

學校郵箱：hengxu@cityu.edu.mo

辦公電話：(853)8590 2397

辦公地址：澳門城市大學(氹仔)何鴻燊樓S504室

 

學歷

  • 2025 計算機科學與技術博士, 悉尼科技大學, 澳大利亞悉尼
  • 2021 信息安全碩士,中國地質大學(武漢) 中國湖北
  • 2018 信息安全學士,中國地質大學(武漢) 中國湖北

 

現任

澳門城市大學數據科學學院助理教授

 

研究方向

  • 模型與隱私安全
  • 機器遺忘( Machine Unlearning)

 

研究及出版

論文:

  1. Heng Xu, Tianqing Zhu, Wanlei Zhou, Wei Zhao. Don’t Forget Too Much: Towards Machine Unlearning on Feature Level, IEEE Transactions on Dependable and Secure Computing, 2024. (CCF-A, JCR Q1)
  2. Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, Philip S Yu. Machine Unlearning: A Survey. ACM Computing Surveys. 56, pp: 1-36, 2024. (Highly Cited Paper) (IF=16.6, JCR Q1)
  3. Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, S Yu Philip, Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation. IEEE Transactions on Big Data, 2024. (IF=7.5, JCR Q1)
  4. Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, Wei Zhao, Towards Efficient Target-Level Machine Unlearning Based on Essential Graph. IEEE Transactions on Neural Networks and Learning Systems. (IF=10.4, JCR Q1)
  5. Xiaocui Dang, Priyadarsi Nanda, Heng Xu, Manoranjan Mohanty, Haiyu Deng, A Novel Scheme For Recommendation Unlearning Verification (RUV) Using Non-influential Trigger Data. International Conference on Security of Information and Networks, 2024. (Australia CORE C)
  6. Xiaocui Dang, Priyadarsi Nanda, Heng Xu, Haiyu Deng and Manoranjan Mohanty, Recommendation System Model Ownership Verification via Non-influential Watermarking. IEEE Consumer Communications &Networking Conference, 2025. (Australia CORE B)
  7. Kaiyue Feng, Guangsheng Zhang, Huan Tian, Heng Xu, Yanjun Zhang, Tianqing Zhu, Ming Ding, and Bo Liu, RAGLeak: Membership Inference Attacks on RAG-based Large Language Models. The 30th Australasian Conference on Information Security and Privacy 2025. (CCF-C)
  8. Peng Huang, Mengyao Hou, Tong Sun, Heng Xu, Chuanming Ma, Aiguo Zhou, Sustainable groundwater management in coastal cities: Insights from groundwater potential and vulnerability using ensemble learning and knowledge-driven models, Journal of Cleaner Production, 442, 141152, 2024. (IF=9, JCR Q1)
  9. Fan Yang, Chaoqun Zhu, Heng Xu, Yongfeng Qian, Jun Song. An efficient malicious webpage static detection framework based on optimized Bayesian and hybrid machine learning. Concurrency and Computation: Practice and Experience, 34(10), 2021. (Best Paper Award) (CCF C)
  10. Yizhi Liu, Chaoqun Zhu, Yadi Wu, Heng Xu and Jun Song. MMWD: An efficient mobile malicious webpage detection framework based on deep learning and edge cloud. Concurrency and Computation: Practice and Experience, 33(18), 2021. (CCF C)
  11. Weihua Hua, Heng Xu, Jianchao Duan, Jun Song, Fan Yang. VMPS: A Vector Map Protection Framework Supporting Dynamic Game and Local Desensitization. Research Square, 2022.
  12. Junru Peng, Heng Xu, Jun Song, HRSE: A novel high-speed random sampling encryption scheme on big data, in Proc of 15th International Conference on Big Data Science and Engineering, pp. 57-64. 2021.
  13. Fan Yang, Zhao Ma, Heng Xu, An Efficient Redundancy Control and Load Balancing Scheme for Cloud Storage, in Proc of 15th International Conference on Big Data Science and Engineering, pp. 49-56, 2021.

专利:

  1. 一種PowerPoint演示文稿向Word文檔轉換的方法及繫統, 排名第二,已授權,授權公告號:CN110222317B.
  2. 一種Word文檔向PowerPoint文檔轉換的方法及繫統, 排名第二,已授權,授權公告號CN110083580B.
  3. 一種Beamer演示文稿向PowerPoint演示文稿轉換的方法及繫統, 排名第二,已授權,授權公告號CN109918351B.
  4. 基於JAVA實現由Word文檔向LaTeX文檔轉換的方法及繫統, 排名第二,已授權,授權公告號CN109918622B.
  5. 一種Word文檔向LaTeX文檔轉換的方法及繫統, 排名第二,已授權,授權公告號CN110147530B.
  6. 一種LaTeX文檔向Word文檔轉換的方法及繫統, 排名第二,已授權,授權公告號CN110147534B.
  7. 一種PowerPoint演示文稿向Beamer演示文稿轉換方法及繫統, 排名第三,已授權,授權公告號CN109885818B.
  8. 一種二維碼安全標籤登錄繫統, 排名第四,已授權,授權公告號:CN109214161B.
  9. 一種基於博弈輪的矢量地圖最優化局部脫敏方法, 排名第四,已授權,授權公告號:CN113051357B.
  10. 一種麵向地質、地理大數據的高速隨機抽樣加密方法, 排名第四,已授權,授權公告號:CN113098843B.
  11. 一種麵向移動噁意網頁的多設備組合優化的實時檢測繫統, 排名第四,已授權,授權公告號:CN113055890B.
  12. 一種基於生成式對抗網絡的涉密地理表格類數據保護方法, 排名第四,已授權,授權公告號:CN113051604B.
  13. 一種基於時效控製的文件訪問方法、設備及存儲設備, 排名第五,已授權,授權公告號:CN108400966B.
  14. 一種文件匿名審批方法, 排名第六,已授權,授權公告號:CN107948161B.
  15. 一種嵌套式二維碼攻擊雙重檢測方法及繫統, 排名第六,已授權,授權公告號:CN109145675B.
  16. 一種幻燈片批注添加及整合新方法, 排名第七,已授權,授權公告號:CN108010107B.
  17. 一種雙模態生物特徵加密方法、設備及存儲設備, 排名第八,已授權,授權公告號:CN109614804B.

 

學術獎項

2024年度中國國家優秀自費留學生獎學金 2025

  1. ARC Discover Project Scholarship，悉尼科技大學 2022–2025
  2. International Research Scholarship，悉尼科技大學 2022–2025
  3. ARC Linkage Project Scholarship top-up. 悉尼科技大學 2022 - 2025
  4. 第四屆中國研究生移動終端應用設計創新大賽一等獎 2018
  5. 第十屆全國大學生資訊安全競賽資訊安全作品賽二等獎 2017