Social power for privacy protected opportunistic networks

Abstract

Opportunistic networking poses a trade off. On the one hand, social links and the structure inherent in the opportunistic network are private information and should thus be protected. On the other hand, such information can be used to improve performance or security. We present an algorithm that can solve this dilemma: we can recognize pre-established social links among nodes without revealing private information, thus enabling privacy and performance and security. Our algorithm uses a hash-based approach for identity protection to reliably and efficiently detect existing social links in an anonymous environment. We implemented our algorithm in a smartphone application and evaluate its performance. Friendship detection time grows linearly with the number of friendships; for example, with 500 friendships, detection typically takes about 90 ms.