We propose a Byzantine-resilient federated conformal prediction (FCP) method that leverages partial model sharing, where only a subset of model parameters is exchanged each round. Unlike existing robust FCP approaches that primarily harden the calibration stage, our method protects both the federated training and conformal calibration phases. During training, partial sharing inherently restricts the attack surface and attenuates poisoned updates while reducing communication. During calibration, clients compress their non-conformity scores into histogram-based characterization vectors, enabling the server to detect Byzantine clients via distance-based maliciousness scores and to estimate the conformal quantile using only benign contributors. Experiments across diverse Byzantine attack scenarios show that the proposed method achieves closer-to-nominal coverage with substantially tighter prediction intervals than standard FCP, establishing a robust and communication-efficient approach to federated uncertainty quantification.

翻译：我们提出一种具有拜占庭鲁棒性的联邦共形预测（FCP）方法，该方法利用部分模型共享策略，每轮仅交换模型参数的一个子集。与现有主要强化校准阶段的鲁棒FCP方法不同，我们的方法同时保护联邦训练和共形校准两个阶段。在训练过程中，部分共享机制天然限制了攻击表面，衰减了恶意更新的影响，同时降低了通信开销。在校准阶段，客户端将其非一致性分数压缩为基于直方图的表征向量，使服务器能够通过基于距离的恶意性分数检测拜占庭客户端，并仅利用良性贡献者估计共形分位数。在不同拜占庭攻击场景下的实验表明，与标准FCP相比，所提方法在实现更接近名义覆盖率的同时，生成了显著更窄的预测区间，从而建立了一种鲁棒且通信高效的联邦不确定性量化方法。