Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption

arXiv:2403.11166v1 Announce Type: new
Abstract: The escalating focus on data privacy poses significant challenges for collaborative neural network training, where data ownership and model training/deployment responsibilities reside with distinct entities. Our community has made substantial contributions to addressing this challenge, proposing various approaches such as federated learning (FL) and privacy-preserving machine learning based on cryptographic constructs like homomorphic encryption (HE) and secure multiparty computation (MPC). However, FL completely overlooks model privacy, and HE has limited extensibility (confined to only one …

arxiv challenge challenges community cs.cr cs.lg data data ownership data privacy deployment entities federated federated learning focus model training network neural network non ownership privacy private responsibilities training