Towards the integration of Privacy-Preserving technologies in future mobile networking

The next generation of mobile networks aims to support data exchange, processing, and collaborative analysis among different parties. This includes distributed machine-learning solutions, that require specific support within the network for secure and privacy-preserving data exchange, also in the light of strict regulations issued by different countries. However, the main challenge relies on privacy-aware data sharing, which mainly concerns sharing data between two entities in a masked form although a minimum level of privacy must be guaranteed.In this paper, we argue for adopting privacy-preserving architectures and algorithms for data sharing, which are necessary for various use cases in next-generation mobile networking. We also propose metrics for evaluating privacy-preserving solutions and benchmark some baseline strategies against datasets used for common tasks in distributed machine-learning solutions.