中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Interactive Anomaly Detection in Dynamic Communication Networks

文献类型：期刊论文

作者Meng, Xuying3,4; Wang, Yequan4; Wang, Suhang2; Yao, Di4; Zhang, Yujun1,4
刊名IEEE-ACM TRANSACTIONS ON NETWORKING
出版日期2021-12-01
卷号29期号:6页码:2602-2615
关键词Anomaly detection Communication networks Feature extraction Estimation Adaptation models Internet Task analysis Anomaly detection interactive learning dynamic networks communication networks semi-parametric bandits
ISSN号1063-6692
DOI10.1109/TNET.2021.3097137
英文摘要Network flows are the basic components of the Internet. Considering the serious consequences of abnormal flows, it is crucial to provide timely anomaly detection in dynamic communication networks. To obtain accurate anomaly detection results in dynamic networks, supervision from experts is highly demanded. However, to obtain high-quality ground truth of abnormal flows, we suffer from two major problems: (1) limited labor resources: experts with the latest domain knowledge are much fewer than the large number of flows; and (2) dynamic environment: considering the new abnormal patterns (i.e., new attacks) and continuously changing network structures, it requires timely supervision to adaptively update the parameters. To tackle these problems, we propose HADDN, a novel bandit framework for periodic-updated anomaly detection in dynamic communication networks. We formulate the task as a bandit problem, where by interactions, supervision is offered by human experts to provide the ground truth to a fraction of flows. We construct semi-parametric expected rewards to optimize the estimation of flows' abnormality in limited interactions. Also, we utilize feature-based clusters and structural correlations to make connections between historical flows and new flows to improve both efficiency and accuracy of abnormality estimation. What's more, we provide two implementations for the semi-parametric expected reward of the proposed HADDN with theoretical proof. Experimental evaluations on public datasets demonstrate the substantial improvement of our proposed approaches compared to state-of-art anomaly detection methods.
资助项目National Science Foundation of China[61902382] ; National Science Foundation of China[61972381] ; National Science Foundation of China[62002343] ; Research Program of Network Computing Innovation Research Institute[E061010003] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDC02030500] ; Key Deployment Project of the Chinese Academy of Sciences[KFZD-SW-440]
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000731147300020
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/17978]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Yujun
作者单位1.Univ Chinese Acad Sci, Dept Comp Sci & Technol, Beijing 100049, Peoples R China
2.Penn State Univ, Coll Informat Sci & Technol, University Pk, PA 16802 USA
3.Purple Mt Labs, Nanjing 211111, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Meng, Xuying,Wang, Yequan,Wang, Suhang,et al. Interactive Anomaly Detection in Dynamic Communication Networks[J]. IEEE-ACM TRANSACTIONS ON NETWORKING,2021,29(6):2602-2615.
APA Meng, Xuying,Wang, Yequan,Wang, Suhang,Yao, Di,&Zhang, Yujun.(2021).Interactive Anomaly Detection in Dynamic Communication Networks.IEEE-ACM TRANSACTIONS ON NETWORKING,29(6),2602-2615.
MLA Meng, Xuying,et al."Interactive Anomaly Detection in Dynamic Communication Networks".IEEE-ACM TRANSACTIONS ON NETWORKING 29.6(2021):2602-2615.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。