Abstract
Crossdomain collaboration allows smart devices work together in different Internet of Things (IoT) domains. Trusted third party-based solutions require to fully understand the access information of the collaboration participants to implement crossdomain access control, which brings privacy risk. In this paper, we propose a federated learning-based crossdomain access decision-making method (FCAD), which builds a crossdomain access decision-making model without sharing privacy information of collaboration participants. Crossdomain access logs are extracted to construct a training dataset. Data enhancement method is used to address the uneven distribution of the dataset. Federated learning and gradient aggregation methods are used to prevent privacy leaks. The experiments on the public dataset show that FCAD obtains a prediction accuracy of 83.6% in the existing crossdomain access system.
Highlights
Internet of Things (IoT) allows connections of heterogeneous smart devices
By using a data enhancement algorithm, the logs are transformed as the input of learning algorithms (ii) We propose a federated learning-based crossdomain access decision-making method (FCAD), to build a crossdomain access decision-making model
The model can decide whether to allow or deny the crossdomain access requests without sharing privacy information of collaboration participants (iii) We evaluate the effectiveness of FCAD on a public dataset
Summary
Internet of Things (IoT) allows connections of heterogeneous smart devices. More than 25 billion smart devices will be connected through IoT by 2025 [1]. The National Health Information Network (NHIN) [3] unites IoT domains of multiple hospitals by providing a trusted third party platform, to form a virtual alliance of medical systems This alliance guarantees the freedom of information flowing between doctors and patients and implements the crossdomain access control. The IoT platform makes access decision and translates user rules to requests in different domains, to achieve crossdomain collaboration. In the crossdomain collaboration system using federated learning, local access logs will not be shared Participants use their local access logs to train their own models. The model can decide whether to allow or deny the crossdomain access requests without sharing privacy information of collaboration participants (iii) We evaluate the effectiveness of FCAD on a public dataset.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
