基于角色代理模型的网格计算环境授权机制研究

分析了目前网格计算中最流行的安全机制GSI和基于GSI的CAS,提出了一种基于本地角色授权的、能够解决大规模虚拟组织授权问题的方案。同GSI和传统的CAS的用户不同的是,本方案中的用户只需要进行本地认证就能够根据其在本地组织的角色来访问虚拟组织。

基于自治系统的多级网格安全模型研究

针对网格环境下用户和资源数量巨大所带来的管理困难、系统单点失效以及可扩展性差等问题,提出了一种基于自治系统的多级网格安全管理模型。该模型通过提取网格资源的共性进行自治系统的划分,根据用户访问资源的所属关系执行不同的安全策略。最后在软件平台下对该安全模型的性能进行了仿真和分析,测试结果表明,该模型对保障网格安全行之有效,有效地减小了管理服务器的负荷,缩短了授权时间,性能得到了提高。

关于网格计算授权机制的研究

分析了目前网格计算中最流行的安全机制GSI(GridSecurityInfrastructure,网格安全基础设施)和基于GSI的CAS(CommunityAuthorizationService,组织授权服务),提出了一种基于本地角色授权的、能够解决大规模VO(VirtualOrganization,虚拟组织)的授权问题的方案。同GSI和CAS不同的是,本方案中的用户只需要进行本地认证就能够根据其在本地组织的角色来访问VO。

Agent based automated trust negotiation model

To enhance the practicability of the trust negotiation system, an agent based automated trust negotiation model （ABAM） is proposed. The ABAM introduces an agent to keep the negotiation process with no human intervention. Meanwhile, the ABAM specifies the format of a meta access control policy, and adopts credentials with flexible format to meet the requirements of access control policies instead of disclosing the whole contents of a certificate. Furthermore, the ABAM uses asymmetric functions with a high security intensity to encrypt the transmitting message, which can prevent information from being attacked. Finally, the ABAM presents a new negotiation protocol to guide the negotiation process. A use case is studied to illuminate that the ABAM is sound and reasonable. Compared with the existing work, the intelligence, privacy and negotiation efficiency are improved in the ABAM.