arXiv：cs.LG· Dominik Roy George, Varesh Mishra, Aysajan Abidin·· 9 小时前AI 评分32
PoCoFL：策略合规的联邦学习框架
PoCoFL: POlicy-COmpliant Federated Learning
AI 导读
PoCoFL 是一个策略合规的联邦学习框架，将联邦学习类型、策略语义与密码学实现三者解耦，客户端用承诺和非交互式零知识证明证明其贡献合规，聚合方证明已按所选聚合策略处理被接纳的贡献。该框架给出 vanilla、continual、personalised 和 threshold-encrypted 四种形式化实例，并完成全部四种实例的概念验证实现，表明其可表达复杂策略且不依赖网络拓扑。
正文
Abstract: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.
| Subjects: | Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03650 [cs.CR] |
| (or arXiv:2610.03650v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03650 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dominik Roy George [view email]
[v1]
Fri, 2 Oct 2026 17:33:01 UTC (3,538 KB)
来源：arXiv：cs.LG · arxiv.org