Privacy-aware Berrut Approximated Coded Computing for Federated Learning

arXiv:2405.01704v1 Announce Type: new
Abstract: Federated Learning (FL) is an interesting strategy that enables the collaborative training of an AI model among different data owners without revealing their private datasets. Even so, FL has some privacy vulnerabilities that have been tried to be overcome by applying some techniques like Differential Privacy (DP), Homomorphic Encryption (HE), or Secure Multi-Party Computation (SMPC). However, these techniques have some important drawbacks that might narrow their range of application: problems to work with non-linear functions …

abstract ai model arxiv collaborative computing cs.cc cs.dc cs.it cs.lg data datasets differential differential privacy federated learning math.it privacy strategy training type vulnerabilities