PRISM-FCP: Byzantine-Resilient Federated Conformal Prediction via Partial Sharing

TL;DR

PRISM-FCP introduces a Byzantine-resilient federated conformal prediction framework that employs partial model sharing and maliciousness scoring to enhance robustness and efficiency against adversarial attacks during training and calibration.

Contribution

It presents a novel end-to-end Byzantine-resilient federated conformal prediction method using partial sharing and maliciousness scoring, improving robustness and communication efficiency.

Findings

Maintains coverage guarantees under Byzantine attacks.

Reduces prediction interval inflation compared to standard methods.

Achieves lower mean-square error with partial sharing.

Abstract

We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a Byzantine-resilient federated conformal prediction framework that utilizes partial model sharing to improve robustness against Byzantine attacks during both model training and conformal calibration. 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 nominal coverage guarantees under Byzantine attacks while avoiding the interval inflation observed in standard FCP with reduced communication, providing a robust and communication-efficient approach to federated uncertainty quantification.