Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Model Sharing

We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a communication-efficient Byzantine-robust federated conformal prediction framework that uses partial model sharing to mitigate stochastic model-poisoning attacks during training and histogram-based filtering to mitigate adversarial calibration submissions.

Existing approaches address adversarial behavior only in the calibration stage, leaving the learned model susceptible to poisoned updates.

In contrast, PRISM-FCP mitigates attacks end-to-end.

During training, clients partially share updates by transmitting only $M$ of $D$ parameters per round.

This attenuates the expected energy of an adversary's perturbation in the aggregated update by a factor of $M/D$, yielding lower mean-square error (MSE) and tighter prediction intervals.

During calibration, clients convert nonconformity scores into characterization vectors, compute distance-based maliciousness scores, and downweight or filter suspected Byzantine contributions before estimating the conformal quantile.

Extensive experiments on both synthetic data and the UCI Superconductivity dataset demonstrate that PRISM-FCP maintains near-nominal empirical coverage in the studied Byzantine settings while avoiding the interval inflation observed in standard FCP, with reduced communication.

These results support PRISM-FCP as a robust and communication-efficient approach to federated uncertainty quantification.