Local Graph-homomorphic Processing for Privatized Distributed Systems. (arXiv:2210.15414v1 [cs.CR])

We study the generation of dependent random numbers in a distributed fashion
in order to enable privatized distributed learning by networked agents. We
propose a method that we refer to as local graph-homomorphic processing; it
relies on the construction of particular noises over the edges to ensure a
certain level of differential privacy. We show that the added noise does not
affect the performance of the learned model. This is a significant improvement
to previous works on differential privacy for …

arxiv distributed distributed systems graph processing systems