• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:孙冲冲,徐亚峰,卜东泰,韩港成,胥勋鹏,高 明.恶意弹窗广告攻击检测技术的研究[J].软件工程,2020,23(5):27-30.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
恶意弹窗广告攻击检测技术的研究
孙冲冲,徐亚峰,卜东泰,韩港成,胥勋鹏,高 明
(徐州工程学院信息工程学院,江苏 徐州 221000)
1247477591@qq.com; 50002729@qq.com; 1169545234@qq.com; 609969059@qq.com; 1127635219@qq.com; 2249858875@qq.com
摘 要: 恶意弹窗广告是一种强迫式的广告,这些广告给投放者带来巨大的利益,但是严重影响了用户体验,侵 犯了用户权益,同时也带来很多安全隐患。恶意弹窗广告攻击检测系统采用C/S架构,服务端使用朴素贝叶斯算法根据 训练集生成和更新训练结果,并利用训练结果对客户端发送的弹窗截图文本进行分类预测。客户端包括基础拦截、截图 拦截以及主动拦截三个模块,主动拦截模块使用OCR技术将可疑弹窗截图转化为文本,然后把此文本传给服务端,服 务端加载之前训练集产生的训练结果,利用朴素贝叶斯算法得到此文本的预测结果,客户端根据预测结果确定对此弹窗 是否拦截。本系统实现了弹窗识别拦截的智能化,配置方便,交互界面易于使用。
关键词: 弹窗广告;机器学习;朴素贝叶斯算法;拦截
中图分类号: TP315    文献标识码: A
Research on the Detection Technology of Malicious Pop-up Advertisements Attack
SUN Chongchong, XU Yafeng, BU Dongtai, HAN Gangcheng, XU Xunpeng, GAO Ming
(College of Information Engineering, Xuzhou University of Technology, Xuzhou 221000, China )
1247477591@qq.com; 50002729@qq.com; 1169545234@qq.com; 609969059@qq.com; 1127635219@qq.com; 2249858875@qq.com
Abstract: Malicious pop-up advertisements are imposed on users. These advertisements bring huge benefits to the publishers, but seriously affect user experience, infringe on user rights and interests, and also bring many security risks. The malicious pop-up advertisements attack detection system uses C/S (Client/Server) architecture. The server uses Naive Bayes algorithm to generate and update training results based on the training set, and uses the training results to classify and predict the pop-up screenshot text sent by the client. The client includes three modules: basic interception, screenshot interception, and active interception. The active interception module uses OCR (Optical Character Recognition) technology to convert the suspicious pop-up screenshot into text, and then transmits this text to the server. The server loads the training results generated by the previous training set. The naive Bayesian algorithm is used to obtain the prediction result of this text, and the client determines whether to block the pop-up window according to the prediction result. The system implements the intelligent identi cation and interception of the pop-up window, with convenient con guration and user-friendly interface.
Keywords: pop-up advertisements; machine learning; naive Bayesian algorithm; interception


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫