Memristor Based Autoencoder for Unsupervised Real-Time Network Intrusion and Anomaly Detection

Memristor Based Autoencoder for Unsupervised Real-Time Network Intrusion and Anomaly Detection
复制标题

基于忆阻器的自动编码器用于无监督实时网络入侵和异常检测

DOI:
10.1145/3354265.3354267
复制
发表时间:
2019
期刊:
ICONS '19: Proceedings of the International Conference on Neuromorphic Systems
影响因子:
--
通讯作者:
Md. Shahanur Alam, B. Rasitha
Md. Shahanur Alam, B. Rasitha
中科院分区:
--
文献类型:
--
作者:
Md. Shahanur Alam, B. Rasitha

文献摘要

参考文献

被引文献

相似文献

用于实时网络安全和异常检测的定制低功耗硬件的需求量很大,因为这将允许电池供电的网络设备实现高效的安全性。本文提出了一种基于忆阻器的实时入侵检测系统,以及基于自动编码器的异常检测。入侵检测基于单个自编码器,该系统整体检测准确率为92.91%,其中恶意数据包检测准确率为98.89%。本文描述的系统还能够使用两个自动编码器通过实时在线学习来执行异常检测。使用该系统,我们表明系统会标记异常数据,但随着时间的推移,如果特定数据类型的存在量很大,系统就会停止标记该数据类型。在这些设计中利用忆阻器使我们能够提供用于入侵和异常检测的极低功耗系统,同时几乎不牺牲准确性。
Custom low power hardware for real-time network security and anomaly detection are in great demand, as these would allow for efficient security in battery-powered network devices. This paper presents a memristor based system for real-time intrusion detection, as well as an anomaly detection based on autoencoders. Intrusion detection is based on a single autoencoder, and the overall detection accuracy of this system is 92.91% with a malicious packet detection accuracy of 98.89%. The system described in this paper is also capable of using two autoencoders to perform anomaly detection using real-time online learning. Using this system, we show that anomalous data is flagged by the system, but over time the system stops flagging a particular datatype if its presence is abundant. Utilizing memristors in these designs allows us to present extreme low power systems for intrusion and anomaly detection, while sacrificing little accuracy.
DOI: 10.1007/978-3-319-23201-0_22
发表时间: 2015
期刊: Microelectron. J.
影响因子: --
作者:
J. Dromard;Gilles Roudière;P. Owezarski
通讯作者: P. Owezarski
DOI: 10.1016/j.mejo.2017.05.005
发表时间: 2017-08-01
影响因子: 2.2
作者:
Hasan, Raqibul;Taha, Tarek M.;Yakopcic, Chris
通讯作者: Yakopcic, Chris
DOI: 10.1109/ijcnn.2018.8489735
发表时间: 2018-07
期刊: 2018 International Joint Conference on Neural Networks (IJCNN)
影响因子: --
作者:
Rasitha Fernando;Raqibul Hasan;T. Taha
通讯作者: Rasitha Fernando;Raqibul Hasan;T. Taha
DOI: 10.1145/3264819
发表时间: 2018-12-01
影响因子: 2.2
作者:
Bontupalli, Venkataramesh;Yakopcic, Chris;Taha, Tarek M.
通讯作者: Taha, Tarek M.
基于忆阻器纵横杆的无监督训练
DOI: 10.1109/naecon.2015.7443091
发表时间: 2015
期刊: 2015 National Aerospace and Electronics Conference (NAECON)
影响因子: --
作者:
Raqibul Hasan;T. Taha
通讯作者: T. Taha