Anomaly Detection for Science DMZs Using System Performance Data

Anomaly Detection for Science DMZs Using System Performance Data
复制标题

使用系统性能数据进行科学 DMZ 异常检测

DOI:
10.1109/icnc47757.2020.9049695
复制
发表时间:
2020
期刊:
Networking and Communications
影响因子:
--
通讯作者:
Peisert, Sean
Peisert, Sean
中科院分区:
--
文献类型:
--
作者:
Gegan, Ross;Mao, Christina;Ghosal, Dipak;Bishop, Matt;Peisert, Sean

文献摘要

参考文献

相似文献

科学DMZ是支持大规模分布式科学研究的专用网络,在以高速率传输大量数据的同时提供高效和有保证的性能。科学DMZ的高速性能是通过数据传输节点(DTN)实现的,因此它们是故障的关键点。DTN通常由网络入侵检测系统(NIDS)监控。然而,NIDS不考虑系统性能数据,例如网络I/O中断和上下文切换,这也可以用于揭示由于基于外部网络的攻击或内部攻击而可能产生的异常系统性能。在本文中,我们演示了如何系统的性能指标可以应用于确保DTN在科学DMZ网络。具体来说,我们评估的有效性,系统性能数据检测TCP-SYN洪水攻击DTN使用DBSCAN(一种基于密度的聚类算法)的异常检测。我们的研究结果表明,系统中断和上下文切换可以用来成功地检测TCP-SYN洪水,这表明系统性能数据可以有效地检测各种攻击不容易通过网络监控单独检测。
Science DMZs are specialized networks that enable large-scale distributed scientific research, providing efficient and guaranteed performance while transferring large amounts of data at high rates. The high-speed performance of a Science DMZ is made viable via data transfer nodes (DTNs), therefore they are a critical point of failure. DTNs are usually monitored with network intrusion detection systems (NIDS). However, NIDS do not consider system performance data, such as network I/O interrupts and context switches, which can also be useful in revealing anomalous system performance potentially arising due to external network based attacks or insider attacks. In this paper, we demonstrate how system performance metrics can be applied towards securing a DTN in a Science DMZ network. Specifically, we evaluate the effectiveness of system performance data in detecting TCP-SYN flood attacks on a DTN using DBSCAN (a density-based clustering algorithm) for anomaly detection. Our results demonstrate that system interrupts and context switches can be used to successfully detect TCP-SYN floods, suggesting that system performance data could be effective in detecting a variety of attacks not easily detected through network monitoring alone.
DOI: 10.1093/jamia/ocw032
发表时间: 2016-11
期刊: Journal of the American Medical Informatics Association : JAMIA
影响因子: --
作者:
Peisert S;Barnett W;Dart E;Cuff J;Grossman RL;Balas E;Berman A;Shankar A;Tierney B
通讯作者: Tierney B
DOI: --
发表时间: 2014
期刊: Journal of management science
影响因子: --
作者:
อนิรุธ สืบสิงห์
通讯作者: อนิรุธ สืบสิงห์
Flowzilla:一种检测研究网络中数据传输异常的方法
DOI: 10.1109/indis.2018.00004
发表时间: 2018
期刊: 2018 IEEE/ACM Innovating the Network for Data-Intensive Science (INDIS)
影响因子: --
作者:
Anna Giannakou;D. Gunter;S. Peisert
通讯作者: S. Peisert
DOI: 10.1109/comst.2018.2876086
发表时间: 2019
影响因子: 35.6
作者:
Crichigno, Jorge;Bou-Harb, Elias;Ghani, Nasir
通讯作者: Ghani, Nasir
检测基于 TCP 的隐秘 DoS 攻击
DOI: 10.1109/milcom.2015.7357467
发表时间: 2015
期刊: MILCOM 2015 - 2015 IEEE Military Communications Conference
影响因子: --
作者:
Azeem Aqil;A. Atya;T. Jaeger;S. Krishnamurthy;K. Levitt;P. Mcdaniel;J. Rowe;A. Swami
通讯作者: A. Swami