Enhancing the Privacy Protection in Locations-based Services through Hybrid LSTM

Location-based services are a call for the provision of useful, tailored information to end users at the time of need. Today, using location-based services (LBS) is a necessary component of our daily life. There are a number of applications of LBS which have major significant in daily lives of a user. Location privacy is a special type of information confidentiality wherein the controlling location information is the core issue. In this paper, a systematic survey is performed over the various methods present so far for privacy protection in LBS. Several possible attacks in LBS are also discussed in this paper. In addition to the systematic survey, a hybrid LSTM model based on deep learning is proposed to increase the effectiveness of the privacy protection techniques in location-based services. The model is expected to provide better performance with improved accuracy and less computational time.