吕明琪

个人基本情况

        吕明琪，教授、博导，浙江工业大学地理信息学院时空信息与智能计算研究所执行所长，浙江大学计算机科学与技术专业博士，曾任南洋理工大学计算机工程学院Research Fellow，浙江省计算机学会人机交互专委秘书长。在基础理论研究方面，长期从事时空人工智能、时空数据挖掘、数据驱动安全等领域的研究工作，主持/参与国家自然科学基金联合重点项目、国家自然科学基金面上项目、浙江省自然科学基金重点项目、浙江省“尖兵”研发攻关计划项目等省部级以上科研项目10余项。在IEEE TDSC、TIFS、TMC、TCYB、TITS、ACM CCS、KDD、UbiComp等国际顶级期刊和会议上发表学术论文100余篇（H指数23），授权国家发明专利40余项，先后获得浙江省技术发明二等奖、中国电子学会科技进步二等奖、日内瓦成果金奖、中国民营科技促进会科技进步二等奖等奖项。在行业应用研究方面，近年来聚焦低空经济、智慧城市等领域的数智化建设，承担了浙江省首个低空空域治理的“尖兵”项目，研制了“久宇”低空仿真系统、“久宇”多模态大模型、物联网时空数据运维系统等，相关成果应用在中国移动智慧家庭安全大脑、中烟工业生产运维系统、北京智网易联的“智飞”低空空域管控平台、浙江鸿程智慧城市研究院空气质量智能监测系统中。

主要研究方向

1. 低空具身智能

        围绕无人机的智能导航、智慧巡检等应用，具体研究低空视觉检测模型、视觉语言导航模型、多模态融合感知算法、无人机飞控智能体等内容。 

2. 时空人工智能

        围绕多模态时空大模型构建的目标，具体研究面向多维时序、地理信息、视觉语言、实景三维等时空数据的大模型架构、微调、推理、智能体等的优化方法，及其在智慧城市、智慧交通、智慧环境等领域的应用。

3. 智能网络安全

        围绕网络攻击检测和防护的目标，具体研究融合网络流量、内核日志、软件代码等多源数据的网络攻击智能检测模型，以及基于威胁情报和大模型的网络攻击防护和运维方法。

时空人工智能相关论文

1. APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-Training. ACM KDD, 2026.     (数据挖掘顶会, CCF A)

2. TrapCog: An Anti-Noise, Transferable, and Privacy-Preserving Real-Time Mobile User Authentication System With High Accuracy. IEEE Transactions on Mobile Computing, 2023.     (移动计算顶刊, CCF A)

3. SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition. IEEE Transactions on Mobile Computing, 2021.     (移动计算顶刊, CCF A)

4. Private Cell-ID Trajectory Prediction Using Multi-Graph Embedding and Encoder-Decoder Network. IEEE Transactions on Mobile Computing, 2021.     (移动计算顶刊, CCF A)

5. EspialCog: General, Efficient and Robust Mobile User Implicit Authentication in Noisy Environment. IEEE Transactions on Mobile Computing, 2020.     (移动计算顶刊, CCF A)

6. Temporal multi-graph convolutional network for traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems, 2020.     (智慧交通顶刊, JCR高被引论文, 引用次数354)

7. Bi-view semi-supervised learning based semantic human activity recognition using accelerometers. IEEE Transactions on Mobile Computing, 2018.     (移动计算顶刊, CCF A)

8. A sequence-to-sequence model for cell-ID trajectory prediction. UbiComp, 2019.     (普适计算顶会, CCF A)

9. Cost-Sensitive Semi-Supervised Personalized Semantic Place Label Recognition Using Multi-Context Data. UbiComp, 2017.     (普适计算顶会, CCF A)

10. Spatially fine-grained urban air quality estimation using ensemble semi-supervised learning and pruning. UbiComp, 2016.     (普适计算顶会, CCF A)

11. UniProv: A unified pretraining framework for provenance graph representation learning. Neurocomputing, 2026.

12. MADGuard: A High-Performance Microservice Anomaly Detection System With Multidimensional Data Fusion and Temporal Causal Analysis. IEEE Transactions on Network and Service Management, 2025.

13. Event-Triggered Distributed Fusion Estimation for Clustered Sensor Networks With Multiscale Fading and Multirate Sampling Characteristics. IEEE Transactions on Control of Network Systems, 2025.

14. SAWD-AC: A spring-based adaptively weighted dual-stream model for aeromagnetic compensation. Information Sciences, 2025.     (CCF B期刊)

15. A Multi-Graph Attentive Network for Traffic Speed Prediction and Diagnosis. IET Intelligent Transport Systems, 2025.

16. AARGNN: An Attentive Attributed Recurrent Graph Neural Network for Traffic Flow Prediction Considering Multiple Dynamic Factors. IEEE Transactions on Intelligent Transportation Systems, 2022.     (智慧交通顶刊, CCF B)

17. An interpretable outcome prediction model based on electronic health records and hierarchical attention. International Journal of Intelligent Systems, 2021.

18. A Knowledge-Based Semisupervised Hierarchical Online Topic Detection Framework. IEEE Transactions on Cybernetics, 2019.     (CCF B期刊)

19. Discovering individual movement patterns from cell-id trajectory data by exploiting handoff features. Information Sciences, 2019.     (CCF B期刊)

20. Air quality estimation by exploiting terrain features and multi-view transfer semi-supervised regression. Information Sciences, 2019.     (CCF B期刊)

21. A hybrid deep convolutional and recurrent neural network for complex activity recognition using multimodal sensors. Neurocomputing, 2019.

22. Hierarchical online NMF for detecting and tracking topic hierarchies in a text stream. Pattern Recognition, 2018.     (CCF B期刊)

23. The discovery of personally semantic places based on trajectory data mining. Neurocomputing, 2016.

智能网络安全相关论文

1. Zoomer: An APT TTP Recognition System Via Deep & Wide Provenance Graph Learning. IEEE Transactions on Dependable and Secure Computing, 2025.     (网络安全顶刊, CCF A)

2. CRUcialG: Reconstruct Integrated Attack Scenario Graphs by Cyber Threat Intelligence Reports. IEEE Transactions on Dependable and Secure Computing, 2025.     (网络安全顶刊, CCF A)

3. TAGAPT: Toward Automatic Generation of APT Samples With Provenance-Level Granularity. IEEE Transactions on Information Forensics and Security, 2025.     (网络安全顶刊, CCF A)

4. Dehydrator: Enhancing Provenance Graph Storage via Hierarchical Encoding and Sequence Generation. IEEE Transactions on Information Forensics and Security, 2025.     (网络安全顶刊, CCF A)

5. SParse: Semantic Tracking and Path Analysis for Attack Investigation in Real-Time. IEEE Transactions on Dependable and Secure Computing, 2025.     (网络安全顶刊, CCF A)

6. TREC: APT Tactic / Technique Recognition via Few-Shot Provenance Subgraph Learning. ACM CCS, 2024.     (网络安全四大顶会, CCF A)

7. Nip in the Bud: Forecasting and Interpreting Post- Exploitation Attacks in Real-Time Through Cyber Threat Intelligence Reports. IEEE Transactions on Dependable and Secure Computing, 2024.     (网络安全顶刊, CCF A)

8. APTSHIELD: A Stable, Efficient and Real-Time APT Detection System for Linux Hosts. IEEE Transactions on Dependable and Secure Computing, 2023.     (网络安全顶刊, CCF A)

9. APT-KGL: An Intelligent APT Detection System Based on Threat Knowledge and Heterogeneous Provenance Graph Learning. IEEE Transactions on Dependable and Secure Computing, 2022.     (网络安全顶刊, CCF A)

10. General, Efficient, and Real-Time Data Compaction Strategy for APT Forensic Analysis. IEEE Transactions on Information Forensics and Security, 2021.     (网络安全顶刊, CCF A)

11. Kellect: A Kernel-based efficient and lossless event log collector for windows security. Computers & Security, 2025.     (CCF B期刊)

12. PDCleaner: A multi-view collaborative data compression method for provenance graph-based APT detection systems. Computers & Security, 2025.     (CCF B期刊)

13. HER-PT: An intelligent penetration testing framework with Hindsight Experience Replay. Computers & Security, 2025.     (CCF B期刊)

14. MIRDETECTOR: Applying malicious intent representation for enhanced APT anomaly detection. Computers & Security, 2025.     (CCF B期刊)

15. An Interpretable Network Intrusion Detection Model via Decision Tree Enhanced Deep Attention Network. IET Information Security, 2025.

16. ProvADShield: A Multimodel Ensemble Defender Against Adversarial Attacks on Provenance Graph Host Intrusion Detector. IET Information Security, 2025.

17. LinTracer: An efficient tracking system for cyberattack chains fusing entity and event semantics. Computers & Security, 2024.     (CCF B期刊)

18. CTIMD: Cyber threat intelligence enhanced malware detection using API call sequences with parameters. Computers & Security, 2024.     (CCF B期刊)

19. MVD-HG: multigranularity smart contract vulnerability detection method based on heterogeneous graphs. Cybersecurity, 2024.

20. System-level data management for endpoint advanced persistent threat detection: Issues, challenges and trends. Computers & Security, 2023.     (CCF B期刊)

近年来授权发明专利

1. Complex Network Attack Detection Method Based on Cross-Host Abnormal Behavior Recognition, 美国专利, 2024/06.

2. 一种基于大模型的多维时序数据异常检测方法, 授权公告日: 2026/01.

3. 一种融合多图神经网络的工业系统异常数据流检测与诊断方法, 授权公告日: 2025/10.

4. 一种基于样本增强与对比学习的恶意网络流量分类方法, 授权公告日: 2025/09.

5. 基于多维传感数据的工业系统生产异常检测与诊断方法, 授权公告日: 2025/07.

6. 一种基于ATT&CK攻击知识增强的渗透测试大模型智能体, 授权公告日: 2025/07.

7. 一种基于多智能体的大语言模型自动渗透测试方法, 授权公告日: 2025/04.

8. 基于大模型的动态恶意软件检测模型黑盒对抗扰动方法, 授权公告日: 2025/04.

9. 基于链路对抗识别的主机入侵检测对抗净化方法及装置, 授权公告日: 2025/04.

10. 一种基于攻击技术识别的APT攻击路径推理方法, 授权公告日: 2025/04.

11. 融合可解释模型与大语言模型的入侵检测与诊断方法, 授权公告日: 2025/02.

12. 一种基于多视图协同学习的主机入侵检测方法和装置, 授权公告日: 2025/02.

13. 一种基于多模型融合的隐匿恶意行为检测方法, 授权公告日: 2024/10.

14. 基于图注意力网络与LSTM自动编码模型的工业系统异常检测方法, 授权公告日: 2024/09.

15. 一种基于程序日志数据的系统异常检测方法, 授权公告日: 2024/04.

16. 一种基于区块链和Handle标识的工业互联网跨域认证方法, 授权公告日: 2024/03.

近年来代表性项目

1. 国家自然科学基金（面上项目），基于多粒度弱监督学习的APT攻击智能检测方法，2024-2027.

2. 浙江省尖兵科技计划项目，复杂低空空域数智化管控关键技术研究及应用，2025-2026.

3. 浙江省自然科学基金（重点项目），数据与知识混合驱动的复杂网络攻击检测方法研究，2023-2025.

4. 浙江省尖兵科技计划项目，超大规模智能物联网可信接入与数据治理关键技术研究，2024-2025.

5. 国家自然科学基金（联合重点项目），面向APT网络攻击链的智能检测与溯源方法及关键技术研究，2020-2023.
   

6. 杭州市重点研发计划项目，面向低空作业的无人机视觉赋能智能巡检系统研发与产业应用，2025-2027.

7. 杭州市重点研发计划项目，工业系统流程监测与态势分析关键技术与应用，2024-2026.

1. 深度学习技术与实践，研究生

2. 移动应用开发，本科生

3. WEB开发技术，本科生

1. 浙江省计算机学会人机交互专委秘书长

2. 中国卫星导航协会低空经济工委会委员

3. CCF杭州分会委员