基于用户画像的异常行为检测模型  

Anomaly Detection Model Based on User Portrait

作　　者：赵刚[1] 姚兴仁 

机构地区：[1]北京信息科技大学信息管理学院,北京100192

出　　处：《信息网络安全》2017年第7期18-24,共7页Netinfo Security

基　　金：国家自然科学基金[61572079];北京市科技重大项目[151100004215003]

摘　　要：入侵检测技术在大数据环境下面临人工规则提取限制、数据处理能力不足、难以精准定位等新问题。文章在入侵检测技术中引入用户画像技术,提出基于用户画像的入侵检测模型,实现入侵检测粒度的细化,将大数据技术引入网络安全领域,发掘其潜在研究及实用价值,使入侵检测技术具有大数据技术特性。实验结果表明,基于用户画像的入侵检测模型能够提高入侵检测技术指标的评价效果,有较好的实用价值。In view of the lack of data processing capability, the manual operation restriction of the rule extraction and the improper positioning ability of the intruderin the current big data environment, cannot meet the new security vulnerabilities and the emergence of the attack means in the new era. The author puts forward the intrusion detection model based on user portraits to realize the refinement of the intrusion detection granularity. In this paper, the intrusion detection model based on user portraits is introduced, and the intrusion detection model based on user image is introduced. To varying degrees, to improve the intrusion detection technology on the measurement of the evaluation results, and to a certain degree of practicality. In addition, as an emerging big data technology, the user portrait technology was introduced from the business areas such as precise marketing into the field of network security, which not only extending the applications of user portrait technology, exploring its potential research and practical value, but also making the intrusion detection technology has big data technology features, that meets the actual needs of the era of big data, and provides a new way to improve the intrusion detection technology at the same time.

关 键 词：用户画像 异常检测 模式匹配 PREFIXSPAN算法 AC_BM算法 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]