Cloud clients face high security risks while sharing physical resources with multiple users. A malicious cloud user exploits co-residency and hypervisor vulnerabilities to steal and hamper sensitive information of victim virtual machine (VM). To address this alarming issue, this Letter proposes a secure resource allocation model by developing a threat detector based on the analysis of co-located inter-VM relations and a workload predictor in the background. The anomalous network traffic, response speed, bandwidth usage and illegal inter-VM links are considered as security breaches indicator that assists in future threat detection beforehand and consequently guides the secure and resource efficient VM allocation. The comparison of proposed model with state-of-the-art: FCFS, Random-fit and NSGA-II based resource allocation approaches indicate that it significantly reduce security threats by 77.38% and number of active servers up to 5.39% with improved resource utilisation up to 26.84% over Random-fit.

中文翻译：

---

云数据中心安全嵌入式动态资源分配模型

云客户端在与多个用户共享物理资源时面临很高的安全风险。恶意云用户利用共存和虚拟机管理程序漏洞窃取和阻碍受害虚拟机（VM）的敏感信息。为了解决这个令人担忧的问题，该信函提出了一种安全资源分配模型，该模型基于对共同定位的VM间关系和后台工作负载预测器的分析，开发了威胁检测器。异常的网络流量，响应速度，带宽使用情况和虚拟机之间的非法链接被视为安全漏洞指标，可预先帮助将来进行威胁检测，从而指导安全且资源高效的虚拟机分配。建议的模型与最新技术的比较：FCFS，