Discrimination-aware trust management for social internet of things

• Published in: Computer networks (Amsterdam, Netherlands : 1999) Netherlands : 1999), 2020-09, Vol.178, p.107254, Article 107254
• Main Authors: Jafarian, Besat, Yazdani, Nasser, Sayad Haghighi, Mohammad
• Format: Article
• Language: English
• Subjects: Cyber security; Data mining; Discrimination; Internet of Things; Object recognition; Provisioning; Social networks; Trust; Trust management; Trustworthiness
• ISSN: 1389-1286; 1872-7069
• DOI: 10.1016/j.comnet.2020.107254

•Context-based trust estimation to service providers.•Detection of discrimination by measuring the correlation between ratings and features like social similarity.•Using a real-world dataset with diverse objects assigned to users for validation. Internet of Things combined with social networks, has emerged as an interesting research area which is referred to as Social Internet of Things (SIoT). Objects in SIoT interact with each other based on their social behavior. In this network, any object can be a service provider or a service consumer. Social objects are expected to be able to easily discover their desired services in a trusted way. Those that belong to humans are usually selfish. Discriminative objects are the ones that do not contribute to providing satisfactory services in some circumstances. By considering discriminative behavior as rational behavior, we introduce a discriminative-aware trust management (DATM) system for service provisioning in SIoT. DATM employs the ratings of objects and is based on a data mining model that compares the context of service query with the contexts of other raters’ previous queries. It takes metrics such as social similarity, importance of the service, and provider's remaining energy into account and takes the problem to a three-dimensional space where weighted-kNN is used to weigh the contribution of each of the k previous experiences in the estimation of trust value. Simulations, in the presence of discriminative and malicious objects, demonstrate that DATM can well detect objects’ selfish behaviors compared to other approaches which ignore social relationships or discrimination in the calculation of trust. Moreover, our scheme resists trust related attacks and does not allow malicious objects to damage the system.