概念漂移下的自适应恶意URL检测

檀国林  张鹏  刘庆云  窦凤虎 



More people use the Internet to shop, access information, etc. But on the other hand, hackers implant malwares (e.g. Trojans, Worms, etc.) in the web pages to steal user information and acquire money illegally, which poses a great risk to the security of cyberspace and the privacy of users. Therefore, it is of great importance to detect malicious URLs in the field of cyberspace security. Different from most of previous methods, in this paper, we propose a method for online malicious URLs detection based on adaptive learning. By collecting the network traffic from backbone networks, we train machine learning models to detect the malicious URLs. But there is a serious problem in dynamically changing environments where the statistical properties of target variable change over time, which is known as concept drift. To address this problem, we apply a nonparametric test to correctly detect concept drifts in adaptive learning. Extensive experiments with different types of concept drifts are performed to demonstrate the feasibility of our proposed method on both artificial and real datasets. Our empirical study shows that this approach has good performance in detecting malicious URLs and concept drifts.




首页
团队介绍
发展历史
组织结构
MESA大事记
新闻中心
通知
组内动态
科研成果
专利
论文
项目
获奖
软著
人才培养
MESA毕业生
MESA在读生
MESA员工
招贤纳士
走进MESA
学长分享
招聘通知
招生宣传
知识库
文章
地址:北京市朝阳区华严北里甲22号楼五层 | 邮编:100029
邮箱:nelist@iie.ac.cn
京ICP备15019404号-1