# Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning

arXiv: https://arxiv.org/abs/2502.00193 · HTML: https://mlsanity.com/paper/2502.00193/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2025.

## Built on by (most cited first, 4 of 4)

- [A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning](https://mlsanity.com/paper/2504.01839/) (2025)
- [Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning](https://mlsanity.com/paper/2506.09870/) (2025)
- [Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning](https://mlsanity.com/paper/2508.12978/) (2025)
- [Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates](https://mlsanity.com/paper/2605.09337/) (2026)

## Abstract (arXiv)

We introduce CyBeR-0, a Byzantine-resilient federated zero-order optimization method that is robust under Byzantine attacks and provides significant savings in uplink and downlink communication costs. We introduce transformed robust aggregation to give convergence guarantees for general non-convex objectives under client data heterogeneity. Empirical evaluations for standard learning tasks and fine-tuning large language models show that CyBeR-0 exhibits stable performance with only a few scalars per-round communication cost and reduced memory requirements.