姓名:范希明
职称:助理研究员
电子邮件:fanximing@scu.edu.cn
办公地点:四川大学江安校区多学科交叉研究创新大楼804
研究方向:二进制漏洞挖掘,AI基础软件安全,智能体安全
个人简介:于2026年在四川大学网络空间安全学院获得工学博士学位,主要研究方向涉及二进制漏洞挖掘验证与利用,模糊测试,AI基础软件漏洞挖掘,智能体漏洞挖掘等。25年来获得CVE编号7项,0day漏洞50余个。在IEEE Transactions on Dependable and Secure Computing,ACM International Conference on the Foundations of Software Engineering,Computers & Security,Information and Software Technology等国际期刊和会议发表多篇论文。
代表性论文:
Ximing Fan, Yong Fang, Peng Jia, t.al. CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries. Proc. ACM Softw. Eng. 3(FSE): 3699-3721 (2026) (CCF-A会议)
Ximing Fan, Yong Fang, Peng Jia, et.al.PS-Fuzz: An Enhanced Fine-Grained Fuzzing Based on Units With Multiple Inputs and Outputs. IEEE Trans. Dependable Secur. Comput. 23(2): 4195-4207 (2026) (CCF-A期刊)
Zhou Y, Jia P, Liu J, Fan X*, et al. Fuzz4Cuda: Fuzzing Your NVIDIA GPU Libraries Through Debug Interface[J]. Computers & Security, 2025: 104754. (CCF-B期刊)
Zuo H, Fang Y, Jia P, Fan X*, et al. Directed fuzzing based on path constraints and deviation path correction[J]. Information and Software Technology, 2025: 107875. (CCF-B期刊)
Xi Peng, Peng Jia, Ximing Fan, Jiayong Liu: ENZZ: Effective N-gram coverage assisted fuzzing with nearest neighboring branch estimation. Inf. Softw. Technol. 177: 107582 (2025) (CCF-B期刊)
Zhu B, Fan X, Gao X, et al. A heterogeneous attention fusion mechanism for the cross-environment scene classification of the home service robot[J]. Robotics and Autonomous Systems, 2024, 173: 104619. (SCI,中科院2区)
授权专利:
朱博, 范希明(2022)基于图卷积神经网络的体素化三维点云场景分类方法 (CN112085066B).
朱博, 谢俊哲, 范希明 (2023). 一种由注意力融合三特征的机器人场景识别与解析方法 (CN 115294441B).