Open Access Open Access  Restricted Access Subscription Access

Trust Based Deep Learning Model for Women Information Security Improvement in LBS

Shrina Patel, Bijal Talati


The pervasiveness of mobile devices equipped with positioning proficiencies has managed to the emergence of frequent location-based applications and services. A huge fraction of the information sought is related to the current women position. This comprises queries for nearby medical services, specialized stores, social activities and groups, and others. In general, location-based service (LBS) operators are expected to be trusted parties that preserve the user’s privacy. Due to the sensitive nature of the information accessed by these parties and recurrent information leakages that have been recorded, the privacy of users that access location-based services is at risk. User’s privacy can be breached by linking one’s identity, location, and query content. On certain scenarios, knowing one’s location is sufficient to derive his identity (e.g. if this location is the user’s residence, office, etc.). In this paper, to address the problem of preserving the location privacy and user anonymity of mobile users accessing authenticated location-based services. To design trust based deep learning model (TBDL) for women information security improvement in LBS that preserve the women user privacy without relying on any trusted entity. A prescribed TBDL model is desirable to theoretically evaluate protection of solutions with respect to specific attack`s Solutions as well it should be empirically validated in terms of performance and quality of service. A considerable effort is essential to acquire realistic or productive real data. Our deep learning model is created to support users to create precise decisions in protecting their location-based privacy.


Location-based Services, Location Privacy, privacy preserving, Activity tracking, deep learning model

Full Text:



  • There are currently no refbacks.

Copyright (c) 2019 Journal of Network Security

  • eISSN: 2395–6739
  • ISSN: 2321–8517