ANCS: Automatic NXDomain Classification System Based on Incremental Fuzzy Rough Sets Machine Learning

ANCS: Automatic NXDomain Classification System Based on Incremental Fuzzy Rough Sets Machine Learning
复制标题

ANCS:基于增量模糊粗糙集机器学习的自动NXDomain分类系统

DOI:
10.1109/tfuzz.2020.2965872
复制
发表时间:
2021-04
影响因子:
11.9
通讯作者:
Chunhua Su
Chunhua Su
中科院分区:
计算机科学1区
文献类型:
--
作者:
Liming Fang;Xinyu Yun;Changchun Yin;Weiping Ding;Lu Zhou;Zhe Liu;Chunhua Su

文献摘要

参考文献

被引文献

相似文献

僵尸主机通过域生成算法(DGAs)生成大量恶意的算法生成域(mAGD)来感染网络上的大量主机,给人们的网络生活带来不便。通过收集域名系统(DNS)的响应来检测mAGD的工作量相当大。在这篇文章中,我们提出了一个名为自动NXDomain分类系统(ANCS)的系统,可以自动识别和分类不存在的域(NXD)为良性或恶意通过研究从良性NXD(bNXDs)和mAGDs提取的功能。ANCS使用在线、增量和模糊粗糙集机器学习来提高检测过程的时间、内存、假阳性率、假阴性率和准确性。首先,在线和增量算法可以减少训练时间。其次,加入模糊粗糙集可以动态调整隶属度函数,优化各特征的权重分配,进一步提高分类精度。实验结果表明,ANCS能够在较低的误报率和漏报率下达到很高的分类精度,具有较好的实用性。同时,ANCS在时间和内存上都有很好的保证,并且具有良好的泛化性能,弥补了噪声样本敏感点和非增量机器学习的不足。
Botmasters generate a large number of malicious algorithmically generated domains (mAGDs) through domain generation algorithms (DGAs) to infect a large number of hosts on a network, which creates inconvenience in people's network lives. The workload of detecting mAGDs by collecting the responses of the domain name system (DNS) is considerable. In this article, we propose a system named the automatic NXDomain classification system (ANCS) that can automatically identify and classify the nonexistent domain (NXD) as benign or malicious by studying the features extracted from benign NXDs (bNXDs) and mAGDs. The ANCS uses online, incremental, and fuzzy rough sets machine learning to improve the time, memory, false positive rate, false negative rate, and accuracy of the detection process. First, an online and incremental algorithm can reduce the training time. Second, the addition of fuzzy rough sets can dynamically adjust the degree of the membership function, optimizing the weight distribution of each feature, and further, improving the classification accuracy. The experimental evaluation shows that the ANCS can reach a very high classification accuracy at a low false positive rate and a low false negative rate, which has good practicability. Moreover, both time and memory are well guaranteed, and the ANCS also has good generalization performance, making up for sensitive points of noisy samples and the lack of nonincremental machine learning.
DOI: 10.4018/ijfsa.2016040103
发表时间: 2016-04
期刊: Int. J. Fuzzy Syst. Appl.
影响因子: --
作者:
A. Chaudhuri
通讯作者: A. Chaudhuri
DOI: --
发表时间: 2012-04
期刊: --
影响因子: --
作者:
D. Dittrich
通讯作者: D. Dittrich
DOI: 10.1017/cbo9780511801389.013
发表时间: 2000-03
期刊: --
影响因子: --
作者:
N. Cristianini;J. Shawe-Taylor
通讯作者: N. Cristianini;J. Shawe-Taylor
DOI: --
发表时间: 2016-08
影响因子: 8.6
作者:
D. Plohmann;Khaled Yakdan;Michael Klatt;Johannes Bader;E. Gerhards-Padilla
通讯作者: D. Plohmann;Khaled Yakdan;Michael Klatt;Johannes Bader;E. Gerhards-Padilla
DOI: 10.1007/978-3-319-08509-8_11
发表时间: 2014-07
期刊: --
影响因子: --
作者:
S. Schiavoni;F. Maggi;L. Cavallaro;S. Zanero
通讯作者: S. Schiavoni;F. Maggi;L. Cavallaro;S. Zanero