一、 主持和参与的部分科研项目: [1] 国家自然科学基金青年项目,62202206,概念漂移现象下基于关联分析的异常网络流量识别方法研究,主持,在研。 [2] 江苏省自然科学基金青年项目,BK20220515,基于概念漂移检测和适应的异常网络流量识别方法研究,主持,在研。 [3] 中国博士后科学基金特别资助(站中)项目,2023T160275,基于数据增强的恶意网络流量检测及攻击溯源方法研究,主持,在研。 [4] 中国博士后科学基金面上项目,2021M691310,基于特征关联分析的网络流量异常检测和识别方法研究,主持,已结题。 [5] 国家自然科学基金面上项目,62172194,面向软件漏洞挖掘的智能化Fuzzing测试方法研究,在研。(排名第二) [6] 国家自然科学基金,U1836116,网络流量中基于数据控制流的漏洞利用程序检测方法研究,已结题。(排名第二) [7] 某部委预研领域基金,61***16,基于缺陷********方法研究,已结题。(排名第二) [8] “十三五”部委预研基金,61***502,物联网软件链漏洞********技术研究,已结题。(排名第三)
二、近年来获得的部分学术成果: (1)部分学术论文(*代表通讯作者) [1] Saihua Cai*, Yingwei Zhao, Jiaao Lyu, et al. DDP-DAR: Network Intrusion Detection Based on Denoising Diffusion Probabilistic Model and Dual-Attention Residual Network. Neural Networks, In press.(SCI,CCF-B,中科院一区) [2] Saihua Cai, Han Tang, Jinfu Chen*, et al. CDDA-MD: An Efficient Malicious Traffic Detection Method based on Concept Drift Detection and Adaptation Technique. Computers & Security, 2025.(SCI,CCF-B,中科院二区) [3] Saihua Cai*, Yingwei Zhao, Yikai Hu, et al. CD-BTMSE: A Concept Drift Detection Model based on Bidirectional Temporal Convolutional Network and Multi-Stacking Ensemble Learning. Knowledge-Based Systems, 294:111681, 2024.(SCI,CCF-C,中科院一区) [4] Saihua Cai, Han Xu, Mingjie Liu, et al. A Malicious Network Traffic Detection Model Based on Bidirectional Temporal Convolutional Network with Multi-Head Self-Attention Mechanism. Computers & Security, 136:103580, 2024.(SCI,CCF-B,中科院二区) [5] Saihua Cai,Li Li, Jinfu Chen, et al. MWFP-Outlier: maximal weighted frequent-pattern-based approach for detecting outliers from uncertain weighted data streams. Information Sciences, 591:195-225, 2022.(SCI,CCF-B,中科院一区) [6] Saihua Cai, Rubing Huang, Jinfu Chen*, et al. An efficient outlier detection method for data streams based on closed frequent patterns by considering anti-monotonic constraints. Information Sciences, 555:125-146, 2021.(SCI,CCF-B,中科院一区) [7] Saihua Cai, Li Li, Sicong Li, et al. An efficient approach for outlier detection from uncertain data streams based on maximal frequent patterns. Expert Systems With Applications, 160:113646, 2020.(SCI,CCF-C,中科院一区) [8] Saihua Cai,Li Li, Qian Li, et al. UWFP-Outlier: an efficient frequent-pattern-based outlier detection method for uncertain weighted data streams. Applied Intelligence, 50:3452-3470, 2020.(SCI,CCF-C,中科院二区) [9] Saihua Cai, Wenjun Zhao, Han Tang, et al. CGSA-RNN: Abnormal Network Traffic Detection Model Based on CycleGAN and Self-Attention Mechanism. In: 23rd IEEE International Conference on Software Quality, Reliability, and Security (QRS 2023), pp. 541-549, 2023.(EI,CCF-C) [10] Jinfu Chen, Jiaping Xu,Saihua Cai,et al. Software Defect Prediction Approach based on A Diversity Ensemble Combined with Neural Network. IEEE Transactions on Reliability, 73(3):1487-1501, 2024.(SCI,CCF-C,中科院二区) [11] [11]Jinfu Chen, Zian Zhao, Saihua Cai*, et al. DCM-GIFT: An Android Malware Dynamic Classification Method based on Gray-scale Image and Feature-Selection Tree. Information and Software Technology, 176:107560, 2024.(SCI,CCF-B,中科院二区) [12]Jinfu Chen, Haodi Xie,Saihua Cai*, et al. GCN-MHSA: A Novel Malicious Traffic Detection Method Based on Graph Convolutional Neural Network and Multi-Head Self-Attention Mechanism. Computers & Security, 147:104083, 2024.(SCI,CCF-B,中科院二区) [13]Jinfu Chen, Luo Song,Saihua Cai*, et al. TLS-MHSA: An efficient detection model for Encrypted Malicious Traffic based on Multi-head Self-Attention Mechanism. ACM Transactions on Privacy and Security, 26(4):44:1-21, 2023.(SCI,CCF-B) [14]Jinfu Chen, Tianxiang Lv, Saihua Cai*, et al. A novel detection model for abnormal network traffic based on bidirectional temporal convolutional network. Information and Software Technology, 157:107166, 2023.(SCI,CCF-B,中科院二区) [15]Jinfu Chen, Yuhao Chen,Saihua Cai*, et al. An optimized feature extraction algorithm for abnormal network traffic detection. Future Generation Computer Systems, 149:330-342, 2023.(SCI,CCF-C,中科院一区) [16]Jinfu Chen, Wei Lin,Saihua Cai*, et al. BiTCN_DRSN: An Effective Software Vulnerability Detection Model based on an Improved Temporal Convolutional Network. Journal of Systems & Software, 204:111772, 2023.(SCI,CCF-B,中科院二区) [17]Jinfu Chen, Shengran Wang,Saihua Cai*, et al. A Novel Coverage-gudied Greybox Fuzzing based on Power Schedule Optimization with Time Complexity. In: 37th IEEE/ACM International Conference on Automated Software Engineering (ASE 2022), pp.1-5, 2022.(EI,CCF-A) [18]Jinfu Chen, Jingyi Chen,Saihua Cai*, et al. A Test Case Generation Method of Combinatorial Testing based on t-way Testing with Adaptive Random Testing. In: 32nd IEEE International Symposium on Software Reliability Engineering (ISSRE 2021), pp.83-90, 2021.(EI,CCF-B) [19]陈锦富, 冯乔伟, 蔡赛华*, 等. 基于形式化方法的区块链系统漏洞检测模型. 软件学报, 35(9):4193-4217, 2024.(EI,卓越期刊) [20]陈锦富, 王震鑫, 蔡赛华*, 等. 基于蜕变测试的区块链智能合约漏洞检测方法. 通信学报, 44(10):164-176, 2023.(EI,卓越期刊)
(2)授权或申请的部分发明专利 [1]发明专利:一种基于核主成分分析的二次特征提取及恶意攻击识别方法。发明人:蔡赛华,陈锦富,赵玲玲,等。专利号:ZL 202110659646.0,2021年。 [2]发明专利:一种基于双向时间卷积神经网络的异常网络流量检测方法。发明人:蔡赛华,陈锦富,吕天翔,等。专利号:ZL 202210650965.X,2022年。 [3]发明专利:一种基于最大频繁模式非相似性的异常网络流量检测方法。发明人:蔡赛华,陈锦富,徐波,等。专利号:ZL 202210226905.5,2022年。 [4]发明专利:一种基于漏洞攻击数据库及决策树的攻击程序识别方法。发明人:蔡赛华,陈锦富,秦松铃,等。专利号:ZL 202110659629.7,2021年。 [5]发明专利:一种用于确定最佳的神经网络输入向量长度的方法。发明人:蔡赛华,刘博,陈锦富,等。专利号:ZL 202110659650.7,2021年。 [6]发明专利:一种基于双向时间卷积神经网络与多头自注意力机制的异常网络流量检测方法。发明人:蔡赛华,刘明杰,徐涵,等。申请号:202211409998.1,2022年。 [7]发明专利:一种基于图注意力网络的恶意网络流量检测方法。发明人:蔡赛华,赵文军,陈锦富,等。申请号:202310950685.5,2023年。 [8]发明专利:一种基于循环生成对抗网络和多头自注意力机制的异常流量检测方法。发明人:蔡赛华,赵文军,陈锦富,等。申请号:202311283486.X,2023年。 [9]发明专利:一种基于概念漂移检测和自适应的恶意流量检测方法。发明人:蔡赛华,唐晗,胡佚恺,等。申请号:202410009003.5,2024年。 [10]发明专利:一种基于去噪扩散概率模型和双注意力残差网络的网络入侵检测方法。发明人:蔡赛华,赵英伟,程梦雅,等。申请号:202411676479.0,2024年。
(3)获批的部分软件著作权 [1] 基于模式距离的异常流量检测平台[简称:Pdbandp]V1.0。完成人:蔡赛华,魏忠旺,林敏,等。登记号:2022SR0626385。 [2]基于概念漂移检测的异常网络流量识别平台[简称:ANTICD]V1.0。完成人:蔡赛华,唐晗,赵文军,等。登记号:2023SR0414803。 [3]基于双向时序卷积网络和多头自注意力机制的异常网络流量检测平台[简称:ANTbTCNAte]V1.0。完成人:蔡赛华,陈智霖,刘明杰,等。登记号:2023SR0414802。 [4]基于图注意力网络和决策树的恶意流量检测平台[简称:MTDPGSADT]V1.0。完成人:蔡赛华,赵星宇,赵文军,等。登记号:2023SR1630233。 [5]基于时序卷积网络和多堆叠集成学习的网络流量概念漂移检测平台[简称:CDTCNML]V1.0。完成人:蔡赛华,吴佳旭,赵英伟,等。登记号:2023SR1633973。
|