We propose a decentralized and dependable reputation based trust supporting framework called PeerTrust, focusing on models and techniques for resilient reputation management against feedback aggregation related vulnerabilities, especially feedback sparsity with potential feedback manipulation, feedback oscillation, and loss of feedback privacy. First, we develop a core reputation model with important trust parameters and a coherent trust metric for quantifying and comparing the trustworthiness of participants. We develop decentralized strategies for implementing the trust model in an efficient and secure manner. Second, we develop techniques countering potential vulnerabilities associated with feedback aggregation, among which the most notable ones are a similarity inference scheme to counter feedback sparsity with potential feedback manipulations, and a novel metric based on Proportional, Integral, and Derivative (PID) model to effectively handle strategic oscillating behavior of participants. Third but not the least, we develop privacy-conscious trust management models and techniques to address the leaking of feedback privacy - a serious concern in any decentralized reputation management system. We develop a set of novel probabilistic decentralized privacy-preserving computation protocols for important primitive operations (such as max, min, and topk). We show how feedback aggregation can be divided into individual operations that utilize above primitive protocols through an example reputation algorithm based on kNN classification. We perform experimental evaluations for each of the schemes we proposed and show the feasibility, effectiveness, and cost of our approach. The PeerTrust framework presents an important step forward with respect to developing attack-resilient reputation trust systems.

Collaborators