Author:
Yang Boxiong,Yu Ying,Wang Zeyu,Li Shelei,Xiao Heng,Gao Hualing,Liang Zhiyong,Zhou Xue
Abstract
Abstract
High Performance Computing (HPC), also known as Supercomputing, is widely applied in various fields, which have the advantage of high processing capability and mass storage. Various open business services bring great threat to the network and data security of HPC cluster. This paper proposes a feasible scheme to realize supercomputing information security through multi-layer defense and overheads control according to the experience of operation, management and maintenance of Supercomputer Center for many years. First, this paper puts forward the principle of moderate risk, and gives the principles of design and the implementation for the security protection of Supercomputing Center. Second, this paper presents a security system architecture in coordination with deep collaborative defense. Finally, this paper designs a 4-layer protection scheme on account of the latest network security solutions and the operation and maintenance characteristic of our own supercomputer. Experiments on multi-level defense and overheads control show that the designed scheme takes into account the cost and network security, and obtain prospective results., which is especially suitable for the network security protection of small-scale or medium-scale high-performance computing cluster for engineering application.
Subject
General Physics and Astronomy
Reference31 articles.
1. Autonomous security mechanisms for high-performance computing systems: review and analysis;Hou;Adaptive Autonomous Secure Cyber Systems,2020
2. A security analysis method for supercomputing users’ behavior;Zhu;CSCloud,2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献