We propose a trustworthiness based secure data aggregation scheme with low latency for isolated terminals in 5G and beyond defined STINs. The trustworthiness of the isolated terminals is evaluated by the satellites and the data centers to increase the reliability of the aggregated data. A lightweight trusted special channel establishment method between an isolated terminal and a data center is presented.

We propose an adaptive physical layer key extraction scheme for smart homes by making use of the Received Signal Strength (RSS). Specifically, in our scheme, two smart home devices collect the RSS measurements by probing with each other. Then, the collected measurements are quantized by running the proposed Self-adaptive Lossless Quantization algorithm. Completing these operations, the two smart home devices can obtain the secret key. In our scheme, we design the self-adaptive lossless quantization algorithm to improve the key generation rate.

We proposed COFEL, a novel federated learning system which can both reduce the communication time by layer-based parameter selection and enhance the privacy protection by applying local differential privacy mechanism on the selected parameters. We present COFEL-AVG algorithm for global aggregation and designed layer-based parameter selection method which can select the valuable parameters for global aggregation to optimize the communication and training process. And it can reduce the update data size as only selected part will be transferred.