Building a privacy-preserving semantic overlay for Peer-to-Peer networks

Abstract

Access to the full text of the published version may require a subscription. Abstract-Searching a Peer-to-Peer (P2P) network without using a central index has been widely investigated but proved to be very difficult. Various strategies have been proposed, however no practical solution to date also addresses privacy concerns. RightsBy clustering peers which have similar interests, a semantic overlay provides a method for achieving scalable search. Traditionally, in order to find similar peers, a peer is required to fully expose its preferences for items or content, therefore disclosing this private information. However, in a hostile environment, such as a P2P system, a peer can not know the true identity or intentions of fellow peers.In this paper, we propose two protocols for building a semantic overlay in a privacy-preserving manner by modifying existing solutions to the Private Set Intersection (PSI) problem. Peers in our overlay compute their similarity to other peers in the encrypted domain, allowing them to find similar peers. Using homomorphic encryption, peers can carrying out computations on encrypted values, without needing to decrypt them first.We propose two protocols, one based on the inner product of vectors, the other on multivariate polynomial evaluation, which are able to compute a similarity value between two peers. Both protocols are implemented on top of an existing P2P platform and are designed for actual deployment. Using a supercomputer and a dataset extracted from a real world instance of a semantic overlay, we emulate our protocols in a network consisting of a thousand peers. Finally, we show the actual computational and bandwidth usage of the protocols as recorded during those experiments.

ePRIVO: An Enhanced PRIvacy-preserVing Opportunistic Routing Protocol for Vehicular Delay-Tolerant Networks

“…For instance, with homomorphic encryption -proposed by Rivest et al in 1978 [20] -a node can carry out computations on encrypted values, without needing to decrypt them first. In [21] and PrivHab+ [22], privacy-preserving routing protocols based on additive homomorphic encryption (Paillier cryptosystem [23]) were proposed. The former, which was proposed for peer-to-peer networks, allowed a node to calculate its similarity to other nodes using multivariate polynomial evaluation, meanwhile, the latter, which was proposed as a secure geographical routing protocol for DTNs, allowed nodes to compare their habitats in order to choose the best forwarder for every message, respectively.…”

“…The mechanism addresses the PSI problem [21] by allowing a node, say A, to calculate its similarity to another node, say B, in a private manner.…”

“…A queries B in order to compute the number of common nodes in their neighboring graphs without disclosing the neighboring graphs themselves. The cardinality of the intersection between the two neighboring graphs, which is computed using multivariate polynomial evaluation [21], is used to find the similarity between the two nodes (ζ). Let A → B : < message > denote a message sent from A to B.…”

Anonymity networks and access to information during conflicts: Towards a distributed network organisation

“…This naïve approach scales very poorly in large networks. For this reason, several alternative approaches have been proposed and implemented in subsequent networks that modify the flooding behaviour [29]. The main issue with network flooding is the high network use it can generate.…”