陈鹏
Lecturer (higher education)
Name (Pinyin):chenpeng
E-Mail:003913@nuist.edu.cn
School/Department:软件学院
Education Level:With Certificate of Graduation for Doctorate Study
Business Address:临江楼A1003
Gender:Male
Degree:Doctoral Degree in Science
Status:在岗
Alma Mater:复旦大学
陈鹏,2024年6月获得复旦大学计算机应用技术博士学位,师从中国工程院院士柴洪峰教授。目前主要研究方向为金融科技、可信人工智能和联邦学习等。已在国外相关领域主流期刊和国际会议发表多篇论文。
目前招收2025届软件工程专硕1名,欢迎踏实勤奋、有志于学术研究的同学与我联系(邮箱 pengchen@nuist.edu.cn)。
发表论文(一作/通讯)
[1]Chen, Peng, et al. "A Practical Clean-Label Backdoor Attack with Limited Information in Vertical Federated Learning."2023 IEEE International Conference on Data Mining (ICDM). IEEE, 2023.
[2]Chen, Peng, et al. "Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning." Computers & Security (2023): 103601.
[3]Chen, Peng, et al. "Evfl: An explainable vertical federated learning for data-oriented artificial intelligence systems." Journal of Systems Architecture 126 (2022): 102474.
[4]Guo, Xu, Chen Peng, et al. "Towards transferable adversarial attacks on vision transformers for image classification[J]. Journal of Systems Architecture", 2024, 152: 103155.
[5] Chen, Peng, et al. "Universal Backdoor Defense via Label Consistency in Vertical Federated Learning." International Joint Conference on Artificial Intelligence(IJCAI2025) CCF A类会议.
[6] Yang Jirui, Chen Peng, et al. "Backdoor Attack on Vertical Federated Graph Neural Network Learning." International Joint Conference on Artificial Intelligence(IJCAI2025) CCF A类会议.
[7] Chen, Peng, et al. "A Data Replication Placement Strategy for the Distributed Storage System in Cloud-Edge-Terminal Orchestrated Computing Environments." IEEE Internet of Things Journal 中科院 一区期刊
[8] Yang Jirui, Chen Peng, et al. "UIFV: Data Reconstruction Attack in Vertical Federated Learning." IEEE INTERNATIONAL CONFERENCE ON WEB SERVICES (ICWS 2025) CCF B 类会议
参与科研项目
[1] 国家自然科学基金重点项目: 大数据背景下基于联邦学习的小微企业信用风险评估研究, 2020年12月至2022.12 参与
[2] 国家重点研发项目: 金融科技产品和机构风险分析、预警与处置技术研发, 2022.10至2025.9 参与
[3] 长三角科技创新共同体联合攻关项目:基于下一代人工智能的金融风险监测智能化关键技术研究,2023.12至2026.11 参与