计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 181-188.doi: 10.11896/j.issn.1002-137X.2018.02.032

• 信息安全 • 上一篇    下一篇

一种综合多因素的网页浏览行为认证方法

陈冬祥,丁志军,闫春钢,王咪咪   

  1. 同济大学电子与信息工程学院 上海208401同济大学嵌入式系统与服务计算教育部重点实验室 上海200092,同济大学电子与信息工程学院 上海208401同济大学嵌入式系统与服务计算教育部重点实验室 上海200092,同济大学电子与信息工程学院 上海208401同济大学嵌入式系统与服务计算教育部重点实验室 上海200092,同济大学电子与信息工程学院 上海208401同济大学嵌入式系统与服务计算教育部重点实验室 上海200092
  • 出版日期:2018-02-15 发布日期:2018-11-13
  • 基金资助:
    本文受上海市“科技创新行动计划”高新技术领域项目(16511100900),国家自然科学基金委重点项目(61332008)资助

Authentication Method Synthesizing Multi-factors for Web Browsing Behavior

CHEN Dong-xiang, DING Zhi-jun, YAN Chun-gang and WANG Mi-mi   

  • Online:2018-02-15 Published:2018-11-13

摘要: 在电子交易中,用户通过PC端的浏览器进行交易。由于钓鱼网站等盗号方式的威胁,传统的账号密码认证方式存在着失效的风险。现有的用户网页浏览行为认证方法主要针对用户的某一方面行为进行认证。若对大量用户仅进行单方面行为的认证,则难以区分特征相似用户,会造成认证失效。基于用户浏览网页的序列行为、超链接使用行为和操作浏览器行为的多因素浏览行为特征,采用机器学习方法构建了一种认证方法。实验结果表明,在一定的误报率情况下,该方法的侦测率达到了90%以上。

关键词: 网页浏览,行为认证,多因素,机器学习

Abstract: In the process of electronic trades,users trade through the PC browser.Due to the threats of phishing sites and other hacking way, there is a failure risk in the traditional account-password-authentication mode.The existing methods of user Web-browsing-authentication mainly aim at authenticating one aspect of the user’s behaviors.For a large number of users,if the authentication is done only from the single aspect,it is difficult to distinguish the features among similar users,which will result in authentication invalidation.Based on the sequence behavior of user browsing Web,the behavior of hyperlink usage and browser manipulation,a authentication method synthesizing multi-factors was proposed by using the machine learning method.The experimental results show that this method achieves more than 90% detection rate under a certain false positive rate.

Key words: Web browsing,Behavior authentication,Multi-factors,Machine learning

[1] 艾瑞网 .2017中国电商导购行业研究报告.http://report.iresearch.cn/report_pdf.aspx?id=2957.
[2] 360互联网安全中心.《2016年中国互联网安全报告》.http://zt.360.cn/1101061855.php?dtid=1101062514&did=490278985.
[3] NENADIC A,ZHANG N,BARTON S.A security protocol for certified e-goods delivery[C]∥International Conference on Information Technology:Coding and Computing.2004:22-28.
[4] HUANG L,LIU G.On data security in e-commerce[C]∥2012 IEEE Symposium on Electrical and Electronics Engineering.2012:94-97.
[5] KALAYE M R G,NIK M H,KORDESTANI H.Using tem-plate-based passwords for authentication in e-banking[C]∥Ecommerce in Developing Countries:with Focus on E-security.2013:1-9.
[6] HONG L,JAIN A.Integrating faces and fingerprints for personal identification[C]∥Asian Conference on Computer Vision.1998:16-23.
[7] WANG D,WANG P.Two Birds with One Stone:Two-FactorAuthentication with Security Beyond Conventional Bound[J].IEEE Transactions on Dependable & Secure Computing,2016(99):1.
[8] GE Y,YAN C,DING Z,et al.Web Access Patterns Mining for Individuals with Timing and Link Sequence[J].InformationTechnology Journal,2014,13(4):746-753.
[9] ZHONG J,YAN C,YU W,et al.A Kind of Identity Authentication Method Based on Browsing Behaviors[J].International Symposium on Computational Intelligence & Design,2015,2:279-284.
[10] ABRAMSON M,AHA D W.User Authentication from WebBrowsing Behavior[C]∥FLAIRS Conference.2013.
[11] LIU Q,WANG M M,ZHAO P H,et al.A Behavioral Authentication Method for MobileGesture Against Resilient User Posture[C]∥The 2016 3rd International Conference on Systems and Informatics (ICSAI 2016).2016.
[12] ANIMA B A,JASIM M,RAHMAN K A,et al.User Authentication from Mouse Movement Data Using SVM Classifier[C]∥International Conference on Cryptology & Network Security.2016:692-700.
[13] BARABSI A L.The origin of bursts and heavy tails in human dynamics[J].Nature,2005,5(7039):207.
[14] QUINLAN J R.C4.5:Programs for Machine Learning[M].San Francisco:Morgan Kaufman,1993 .
[15] TAX D M J,DUIN R P W.Support vector domain description[J].Pattern Recognition Letters,1999,20(11-13):1191-1199.
[16] ABDI H,WILLIAMS L J.Principal component analysis[J].Wiley Interdisciplinary Reviews Computational Statistics,2010,2(4):433-459.
[17] SPACKMAN K A.Signal detection theory:Valuable tools for evaluating inductive learning[C]∥Proceedings of the 6th International Workshop on Machine Learning(IWML).Ithaca,NY,1989:160-163.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!