Total views : 115

Secured Client-Side Content Filtering Using Machine Learning Algorithms

Affiliations

  • School of Computer Science, Osmania University, Amberpet, Hyderabad – 500007, Telangana, India
  • Department of Mathematics, Osmania University, Amberpet, Hyderabad – 500007, Telangana, India
  • Department of Electronics and Communication, Osmania University, Amberpet, Hyderabad – 500007, Telangana, India

Abstract


Objectives: The sheer amount of content available in cloud service providers (News, Social media, etc.) poses a fundamental problem for users: The excess amount of diverse information available for public access without regard to age, sex or other classifiers. Methods/Statistical analysis: Ability to filter and control this content while maintaining anonymity is a challenge which isn’t addressed properly, yet. Findings: Previous Solutions proposed to tackle this need integration on either server-side or client-side. However, these solutions seem to have two major drawbacks the ability to maintain client anonymity from the content provider and the ability to integrate server-side filtering with client side filtering. Application/Improvements: In this paper a system is proposed that integrates secured content classification and content filtering based on trained data. Security is achieved by using the identity of the user generated from the initial contact point.

Keywords

Jason Web Token (JWT), Machine Learning, Naive Bayes, Tiny Encryption Algorithm (TEA)

Full Text:

 |  (PDF views: 100)

References


  • Zafarani R, Abbasi MA, Liu H. Social media mining an introduction. Cambridge University Press; 2014 Jan.
  • Chau M, Chen H. A machine learning approach to web page filtering using content and structure analysis. Decision Support Systems. 2008 Jan; 44(2):482–94.
  • Adomavicius A, Tuzhilin G. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. Institute of Electrical and Electronics Engineers (IEEE) Transaction on Knowledge and Data Engineering. 2005 Jun; 17(6):734–49.
  • Chau M, Chen H. A machine learning approach to web page filtering using content and structure analysis. Decision Support Systems. 2008 Jan; 44(2):482–94.
  • Mooney RJ, Roy L. Content-based book recommending using learning for text categorization. In the Proceeding of the Fifth Association for Computing Machinery (ACM) Conference in Digital Libraries; 2000 Jun. p. 195–204.
  • Vanetti M, Binaghi E, Ferrari E, Carminati B, Carullo M. A system to filter unwanted messages from OSN user walls. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Knowledge and Data Engineering. 2013 Feb; 25(2):285–97.
  • Reuters-21578 Text Categorization Collection Data Set [Internet]. 1987 [cited 1987]. Available from: https://archive.ics.uci.edu/ml/datasets/Reuters-21578+Text+Categorization+Collection
  • Porter MF. An algorithm for suffix stripping. Program: Electronic Library and Information Systems. 2006; 40(3):211–8.
  • Implementation of the Tiny Encryption Algorithm [Internet]. 2015 [cited 2015]. Available from: https://github.com/chrisveness/crypto/blob/master/tea-block.js
  • Wheeler DJ, Needham RM. TEA, a tiny encryption algorithm. In: Preneel B editor. International Workshop on Fast Software Encryption. Lecture Notes in Computer Science, Springer, Heidelberg. 1994 Dec 14–16; 1008:363–6.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.