Location sharing with secrecy guarantees in mobile social networks

Aus SDQ-Institutsseminar
Version vom 5. November 2019, 17:19 Uhr von Yifan Bao (Diskussion | Beiträge)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Vortragende(r) Yifan Bao
Vortragstyp Masterarbeit
Betreuer(in) Gabriela Suntaxi
Termin Fr 8. November 2019
Vortragssprache
Vortragsmodus
Kurzfassung With the increasing popularity of location-based services and mobile online social networks (mOSNs), secrecy concerns have become one of the main worries of its users due to location information exposure. Users are required to store their location, i.e., physical position, and the relationships that they have with other users, e.g., friends, to have access to the services offered by these networks. This information, however, is sensitive and has to be protected from unauthorized access.

In this thesis, we aim to offer location-based services to users of mOSNs while guaranteeing that an adversary, including the service provider, will not be able to learn the locations of the users (location secrecy) and the relationship existing between them (relationship secrecy). We consider both linking attacks and collusion attacks. We propose two approaches R-mobishare and V-mobishare, which combine existing cryptographic techniques. Both approaches use, among others, private broadcast encryption and homomorphic encryption. Private broadcast encryption is used to protect the relationships existing between users, and homomorphic encryption is used to protect the location of the users. Our system allows users to query their nearby friends. Next, we prove that our proposed approaches fulfill our secrecy guarantees, i.e., location and relationship secrecy. Finally, we evaluate the query performance of our proposed approaches and use real online social networks to compare their performance. The result of our experiments shows that in a region with low population density such as suburbs, our first approach, R-mobishare, performs better than our approach V-mobishare. On the contrary, in a region with high population density such as downtown, our second approach, V-mobishare, perform better than R-mobishare.