The growing availability of distributed data has led to the increased use of machine learning (ML) algorithms in distributed topologies, where multiple nodes collaborate to train models under the coordination of a central server. However, distributed learning faces two significant challenges: the risk of Byzantine nodes corrupting the learning process by sending incorrect information, and the potential for a curious server to violate the privacy of individual nodes, even reconstructing their private data. While homomorphic encryption (HE) has been a promising solution for privacy preservation in distributed settings, its high computational cost, especially for high-dimensional ML models, has made it challenging to design robust (non-linear) Byzantine-resilient algorithms using HE.

International audience

Abstract We design and implement an efficient, secure, homomorphic k-Nearest Neighbours determination algorithm, to be used for regression or classification over private data. Our algorithm runs in quadratic complexity with regard to the size of the database but is the only one in the literature to make the secure determination completely non-interactively. We show that our secure algorithm is both efficient and accurate when applied to classification problems requiring a small set of model vectors, and still scales to larger sets of model vectors with high accuracy yet at greater (sequential) computational costs.

Software Defined Networking and Network Function Virtualisation provide significantly more flexibility and control when provisioning QoS for delay sensitive services. Network delay can have a detrimental impact on VoIP quality and, therefore, minimising delay can help maintain the quality and prevent call dropping. This paper proposes a queuing scheme based on packet delay for prioritising VoIP calls made over SDN. An OpenFlow testbed was developed to validate our proposal, and results show that delay-based prioritisation of VoIP packets in SDN networks ensures that only a small number of users will be affected by network congestion.