Using Dirichlet Marked Hawkes Processes for Insider Threat Detection

Using Dirichlet Marked Hawkes Processes for Insider Threat Detection
复制标题

使用狄利克雷标记霍克斯过程进行内部威胁检测

DOI:
10.1145/3457908
复制
发表时间:
2022
期刊:
Digital Threats: Research and Practice
影响因子:
--
通讯作者:
Wu, Xintao
Wu, Xintao
中科院分区:
--
文献类型:
--
作者:
Zheng, Panpan;Yuan, Shuhan;Wu, Xintao

文献摘要

参考文献

被引文献

相似文献

恶意内部人员给组织造成重大损失。由于内部人员的恶意活动数量极少,内部威胁很难被检测到。在本文中,我们提出了一个狄利克雷标记霍克斯过程(DMHP),以检测恶意活动的内部人员在实时。DMHP结合了Dirichlet过程和Marked Hawkes过程对用户活动序列进行建模。Dirichlet过程能够检测无限用户活动的无界用户模式(模式),而对于每个检测到的用户模式,采用一组标记的Hawkes过程来从时间和活动类型(例如,WWW访问或发送电子邮件)信息,从而不同的用户模式由不同的标记Hawkes过程集来建模。为了实现实时恶意内部活动检测,采用DMHP计算的最近活动的可能性作为评分来衡量活动的恶意性。由于大多数用户活动都是良性的,因此那些可能性较低的活动被标记为恶意活动。在两个数据集上的实验结果表明了DMHP的有效性。
Malicious insiders cause significant loss to organizations. Due to an extremely small number of malicious activities from insiders, insider threat is hard to detect. In this article, we present aDirichlet Marked Hawkes Process (DMHP)to detect malicious activities from insiders in real-time. DMHP combines the Dirichlet process and marked Hawkes processes to model the sequence of user activities. The Dirichlet process is capable of detecting unbounded user modes (patterns) of infinite user activities, while, for each detected user mode, one set of marked Hawkes processes is adopted to model user activities from time and activity type (e.g., WWW visit or send email) information so that different user modes are modeled by different sets of marked Hawkes processes. To achieve real-time malicious insider activity detection, the likelihood of the most recent activity calculated by DMHP is adopted as a score to measure the maliciousness of the activity. Since the majority of user activities are benign, those activities with low likelihoods are labeled as malicious activities. Experimental results on two datasets show the effectiveness of DMHP.
DOI: 10.1145/2897795.2897799
发表时间: 2016
期刊: Proceedings of the 11th Annual Cyber and Information Security Research Conference
影响因子: --
作者:
Ameya Sanzgiri;D. Dasgupta
通讯作者: D. Dasgupta
DOI: --
发表时间: 2017-01
期刊: --
影响因子: --
作者:
Hongteng Xu;H. Zha
通讯作者: Hongteng Xu;H. Zha
DOI: --
发表时间: 2018
期刊:
影响因子: --
作者:
J. Rasmussen
通讯作者: J. Rasmussen
DOI: 10.1214/06-ba104
发表时间: 2006-01-01
期刊: BAYESIAN ANALYSIS
影响因子: 4.4
作者:
Blei, David M.;Jordan, Michael I.
通讯作者: Jordan, Michael I.
一种基于量子力学的新型异常检测算法
DOI: 10.1109/icdm.2012.127
发表时间: 2012
期刊: 2012 IEEE 12th International Conference on Data Mining
影响因子: --
作者:
Hao Huang;Hong Qin;Shinjae Yoo;Dantong Yu
通讯作者: Dantong Yu