ByzFL: Research Framework for Robust Federated Learning
Reviewed by Pithpith:2JSTOA6Xopen to challenge →
read the original abstract
We present ByzFL, an open-source Python library for developing and benchmarking robust federated learning (FL) algorithms. ByzFL provides a unified and extensible framework that includes implementations of state-of-the-art robust aggregators, a suite of configurable attacks, and tools for simulating a variety of FL scenarios, including heterogeneous data distributions, multiple training algorithms, and adversarial threat models. The library enables systematic experimentation via a single JSON-based configuration file and includes built-in utilities for result visualization. Compatible with PyTorch tensors and NumPy arrays, ByzFL is designed to facilitate reproducible research and rapid prototyping of robust FL solutions. ByzFL is available at https://byzfl.epfl.ch/, with source code hosted on GitHub: https://github.com/LPD-EPFL/byzfl.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Monotonicity of aggregated gradients holds if and only if the aggregation rule is positively affine; non-affine rules therefore prevent steady convergence and degrade stability.
-
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
In Byzantine-robust LDP distributed learning, generalization error decreases with increasing privacy strength in high-noise regimes but increases in low-noise regimes, shown via matching algorithmic stability bounds.
-
Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
Giskard is a new protocol using tree-structured log-sized committees and MPC-based approximate median to achieve scalable confidential and Byzantine-robust aggregation in decentralized learning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.