基于设备指纹决策树分类的IP视频专网入网检测方案研究  

Research on IP Video Network Access Detection Based on Decision Tree Classifi cation of Device Fingerprint

作　　者：尹心明 胡正梁[1] 陈国梁[1] 黄海晔[1] 

机构地区：[1]公安部第三研究所信息安全技术部,上海201204

出　　处：《信息网络安全》2016年第12期68-73,共6页Netinfo Security

摘　　要：由于视频专网中大量的采集设备部署在公共区域,面临的安全问题较多,如何将视频设备安全、高效地接入视频专网是至关重要的。文章提出了一种基于设备指纹决策树分类算法的方案来解决视频专网设备入网检测的问题。该方案根据视频设备特征在操作系统指纹基础上设计了设备指纹,同时提出了视频专网设备指纹的采集方法和存储方法。通过设备指纹的决策树分类算法及时检测出视频专网中的非信任设备,并告警。为防止非法入侵和避免视频专网数据泄露起到重要作用。As a lot of the video dedicated network acquisition equipments deployed in public.areas, face more security issues. How to connect the video equipments safely and efficiently to the video dedicated network is very important. In this paper, we propose a decision tree classification algorithm of device fingerprint to solve the problem, According to the characteristics of the video equipments, we design the device fingerprint on the basis of the operating system fingerprint. Meanwhile, we also propose the collection and storage methods of the device fingerprint. The decision tree classification algorithm of fingerprint equipment can detect the non trusted devices in the video dedicated network, and accompanied by the alarm. In a word, this project can effectively prevent the illegal intrusion and avoid the video dedicated network data leakage.

关 键 词：视频专网入网检测 设备指纹 决策树 信息熵 

分 类 号：TN948.6[电子电信—信号与信息处理] TN915.08[电子电信—信息与通信工程]