arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.04801cs.CRcs.NI
收藏

针对5G多接入边缘计算中的DDoS缓解的改进安全解决方案

Improved security solutions for DDoS mitigation in 5G Multi-access Edge Computing

Marian Gusatu, Ruxandra F. Olimid

摘要:

多访问边缘计算(MEC)是一种支持5G的解决方案,旨在将云计算功能更接近最终用户。本文重点介绍了5G MEC环境下针对分布式拒绝服务(DDoS)攻击的缓解技术,提供了涉及虚拟化环境和MEC架构管理实体的解决方案。建议的解决方案旨在降低DDoS攻击背景下影响合法流量的风险。我们的工作支持的想法,使用网络流收集器发送数据的异常检测系统的基础上,人工智能技术,作为对以前的工作的改进,它有助于重定向检测到的异常隔离到一个单独的虚拟机。该虚拟机使用深度数据包检测工具来分析流量并提供服务,直到最终判决。我们通过隔离可疑流量来降低危害为合法用户提供服务的虚拟机的风险。MEC架构的管理实体允许重新实例化或重新配置虚拟机。因此,如果检查隔离流量的机器由于攻击而崩溃,则可以恢复损坏的机器,而提供给合法用户的服务不受影响。

英文摘要:

Multi-access Edge Computing (MEC) is a 5G-enabling solution that aims to bring cloud-computing capabilities closer to the end-users. This paper focuses on mitigation techniques against Distributed Denial-of-Service (DDoS) attacks in the context of 5G MEC, providing solutions that involve the virtualized environment and the management entities from the MEC architecture. The proposed solutions aim to reduce the risk of affecting legitimate traffic in the context of DDoS attacks. Our work supports the idea of using a network flow collector that sends the data to an anomaly detection system based on artificial intelligence techniques and, as an improvement over the previous work, it contributes to redirecting detected anomalies for isolation to a separate virtual machine. This virtual machine uses deep packet inspection tools to analyze the traffic and provides services until the final verdict. We decrease the risk of compromising the virtual machine that provides services to legitimate users by isolating the suspicious traffic. The management entities of the MEC architecture allow to re-instantiate or reconfigure the virtual machines. Hence, if the machine inspecting the isolated traffic crashes because of an attack, the damaged machine can be restored while the services provided to legitimate users are not affected.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑