基于DBN模型的互联网敏感信息泄露检测研究

Research on internet sensitive information leakage detection based on DBN model

互联网敏感信息存在的噪声影响敏感信息泄露检出率和检测任务完成时间,因此研究基于DBN模型的互联网敏感信息泄露检测方法。利用分布式网络爬虫技术爬取互联网网页敏感信息,采用近邻策略对爬取到的信息进行分组处理,并对分组处理完成的信息进行去噪。将编码和序列化处理过后的互联网敏感信息处理结果输入训练好的DBN模型中,得到互联网敏感信息泄露检测结果。实验结果表明,基于DBN模型的互联网敏感信息泄露检测方法的检出率高达99.8%,检测任务完成时间短,实际应用效果好。

The noise of sensitive information on the Internet affects the detection rate of sensitive information leakage and the completion time of detection tasks.Therefore,the detection method of sensitive information leakage on the Internet based on DBN model is studied.The distributed web crawler technology is used to crawl the sensitive information of Internet pages,and the nearest neighbor strategy is used to group the crawled information and denoise the information that has been grouped.Input the encoded and serialized Internet sensitive information processing results into the trained DBN model to obtain the Internet sensitive information disclosure detection results.The experimental results show that the detection rate of sensitive information leakage detection method based on DBN model is as high as 99.8%,the detection task completion time is short,and the practical application effect is good.