基于Hellinger的社交物联网信任管理矩阵分解模型
A Matrix Factorization Model for Hellinger-based Trust Management in Social Internet of Things
摘要：
已经引入了物联网和社交网络范例的集成的社交物联网（SIoT）来构建能够建立社交链接的智能节点的网络。为了应对行为不端的服务提供者节点，服务请求者节点必须评估其可信度水平。在本文中，我们提出了一种新的信任管理机制，在SIoT预测最可靠的服务提供者为每个服务请求者，从而导致被暴露给恶意节点的风险。我们使用灵活的二分图（包含两组节点：服务提供者和服务请求者）对SIoT进行建模，然后使用Hellinger距离在服务请求者节点之间构建社交网络。之后，我们开发了一个社会信任模型，利用节点的中心性和相似性度量来提取社会网络节点之间的信任行为。最后，设计了一种矩阵分解技术来提取SIoT节点的潜在特征，找到可信节点，并缓解数据稀疏和冷启动问题。我们分析了所提出的信任预测机制中的参数对预测精度的影响。结果表明，从一个特定的服务请求者具有高Hellinger相似性的邻居节点的反馈，在我们的机制优于现有的最好的方法。我们还表明，利用社会信任模型，它只考虑了相似性度量，显着提高了预测机制的准确性。此外，我们通过一个真实的SIoT用例评估了所提出的信任管理系统的有效性。我们的研究结果表明，该机制是弹性的不同类型的网络攻击，它可以准确地找到最合适的和值得信赖的服务提供商。
英文摘要：
The Social Internet of Things (SIoT), integration of the Internet of Things and Social Networks paradigms, has been introduced to build a network of smart nodes that are capable of establishing social links. In order to deal with misbehaving service provider nodes, service requestor nodes must evaluate their trustworthiness levels. In this paper, we propose a novel trust management mechanism in the SIoT to predict the most reliable service providers for each service requestor, which leads to reduce the risk of being exposed to malicious nodes. We model the SIoT with a flexible bipartite graph (containing two sets of nodes: service providers and service requestors), then build a social network among the service requestor nodes, using the Hellinger distance. Afterward, we develop a social trust model using nodes' centrality and similarity measures to extract trust behaviors among the social network nodes. Finally, a matrix factorization technique is designed to extract latent features of SIoT nodes, find trustworthy nodes, and mitigate the data sparsity and cold start problems. We analyze the effect of parameters in the proposed trust prediction mechanism on prediction accuracy. The results indicate that feedbacks from the neighboring nodes of a specific service requestor with high Hellinger similarity in our mechanism outperforms the best existing methods. We also show that utilizing the social trust model, which only considers a similarity measure, significantly improves the accuracy of the prediction mechanism. Furthermore, we evaluate the effectiveness of the proposed trust management system through a real-world SIoT use case. Our results demonstrate that the proposed mechanism is resilient to different types of network attacks, and it can accurately find the most proper and trustworthy service provider.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
