基于BP神经网络的Wi-Fi安全评价模型的研究Wi-信息通信学术期刊网.PDF

第 37 卷第 Z1 期 通 信 学 报 Vol.37 No.Z1 2016 年 10 月 Journal on Communications October 2016 doi:10.11959/j.issn.1000-436x.2016247 基于 BP 神经网络的 Wi-Fi 安全评价模型的研究 康海燕 1 ，闫涵 1 ，黄浩然 2 ，孙璇 1 （1. 北京信息科技大学信息安全系，北京 100192 ；2. 北京北大方正电子有限公司，北京 100085 ） 摘 要：提出了基于 BP 神经网络的 Wi-Fi 安全评价模型。首先，分析了大量 Wi-Fi 热点，选取与无线热点安全 相关的信息源；其次，构造 BP 神经网络模型，并对权值进行调整，形成了有较高可信度的 Wi-Fi 安全性评估体 系；最后，在 Android 平台上，设计了基于 BP 神经网络的 Wi-Fi 安全模型。实验证明，该安全评价模型能够对 用户周边无线热点进行扫描及安全性评估，并提供不安全无线热点断开连接功能。 关键词：Wi-Fi ；智能保护盾；Android ；Wi-Fi 安全评价 中图分类号：TP312 文献标识码：A Wi-Fi security evaluation model based on BP neural network 1 1 2 1 KANG Hai-yan , YAN Han , HUANG Hao-ran , SUN Xuan (1. Department of Information Security, Beijing Information Science and Technology University, Beijing 100192, China; 2. Beijing Founder Electronics Co. Ltd., Beijing 100085, China) Abstract: A Wi-Fi security evaluation model was proposed based on BP neural network. Firstly a large number of Wi-Fi hotspots was analyzed, safety information sources about wireless hotspots were selected. Secondly, a model of BP neural network was constructed, the weights were adjusted, and the evaluation system for Wi-Fi safety was formed, which was higher credibility. Finally, on the Android flatform the application based on above theory was designed. A lot of experi- ments show the model is able to scan and evaluate the wireless hotspot around user. It can also provide the disconnect function on unsafe wireless hotspot. Key words: Wi-Fi, intelligent protection shield, Android, Wi-Fi security evaluation