Improving Privacy of Recommender Agents by Means of Full Dissociation

  • Authors:
  • Sonia Delfin;Claudia Carrillo;Eduard Muntaner;Araceli Moreno;Salvador Ibarra;Josep Lluis de la Rosa

  • Affiliations:
  • Agents Research Lab, University of Girona, Spain;Agents Research Lab, University of Girona, Spain;Agents Research Lab, University of Girona, Spain;Agents Research Lab, University of Girona, Spain;Agents Research Lab, University of Girona, Spain;Agents Research Lab, University of Girona, Spain

  • Venue:
  • Proceedings of the 2006 conference on Artificial Intelligence Research and Development
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Our approach is to give privacy to the profile and behaviour of the user; the state of the art for privacy consists of encryption algorithms, occultation and temporary association of a user's information. In all cases these aspects present pros and cons. A primary disadvantage is that within a certain amount of time an attacker is capable of reconstruct the original information (encryptation), finding the information (occultation) and relating it to the original user (temporary association). In our approach, full dissociation is used to impede any relation with the original user. It is the concept of full dissociation which considerably reduces the available time for an attacker to discover the relation with the original user.