Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
PoCoFL introduces a novel framework for policy-compliant federated learning by decoupling FL type, policy semantics, and cryptographic realization, enabling clients to prove contribution compliance and aggregators to prove correct processing via commitments and non-interactive zero-knowledge proofs. This approach addresses the limitations of existing verifiable FL systems by offering a network-topology agnostic solution applicable across diverse FL settings and aggregation semantics. The framework's versatility is demonstrated through four formal instantiations and proof-of-concept implementations, showing effective policy enforcement without compromising learning objectives.
A single framework now verifies policy compliance in any federated learning setup, from vanilla to personalized, using zero-knowledge proofs without network topology constraints.
Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to participating clients. However, it does not guarantee that clients submit policy-compliant contributions or that aggregators process admitted contributions correctly. Existing verifiable FL systems tailor validation rules to specific FL settings, learning workflows, and cryptographic constructions, limiting their applicability across network topologies, participant roles, and aggregation semantics. In this paper, we present PoCoFL, a policy-compliant federated learning framework that separates three aspects: (i) FL type, (ii) policy semantics, and (iii) cryptographic realisation. We provide a formalisation that captures client and aggregation requirements as policy-dependent relations. Clients prove compliance of their contributions using commitments and non-interactive zero-knowledge proofs, while aggregators prove that the recorded set of admitted contributions was processed according to the selected aggregation policy. We demonstrate PoCoFL through four formal instantiations: (i) vanilla, (ii) continual, (iii) personalised, and (iv) threshold-encrypted federated learning. We evaluate the effects of policy enforcement on the learning objectives of vanilla, personalised, and continual FL. We further implement proof-of-concept realisations of all four instantiations, demonstrating the versatility and practical feasibility of PoCoFL. Overall, these results show that PoCoFL can capture complex policy representations while remaining network-topology agnostic.