← Back to all news
arXiv AI By Edoardo Gabrielli, Gabriele Tolomei

Optimizing Byzantine Node Placement in Decentralized Federated Learning

Read the original on arXiv AI →

The paper investigates how the strategic placement of Byzantine nodes in decentralized federated learning (DFL) affects the propagation of malicious influence across the communication graph. It introduces Byzantine Placement Influence (BPI), a measure that captures cumulative exposure of honest nodes to Byzantine sources over time, and develops algorithms to optimize BPI across various network structures and attack types. Experiments demonstrate that BPI-guided placements consistently yield highly damaging configurations, highlighting the importance of considering node placement in DFL threat models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 26

SketchGuard: Scaling Byzantine-Robust Decentralized Federated Learning via Sketch-Based Screening

SketchGuard is a Byzantine‑robust decentralized federated learning method that separates neighbor screening from model aggregation by using a Count Sketch representation. The approach mitigates a vulnerability where an adaptive adversary can hide large perturbations in the sketch’s null space, by adopting a commit‑then‑sketch protocol that ensures the sketch seed is chosen only after model commitment. The authors prove convergence in both convex and non‑convex settings, demonstrate that SketchGuard achieves state‑of‑the‑art robustness against six attacks—including the adaptive null‑space attack—across various network topologies and data heterogeneity, while reducing per‑neighbor communication to a model‑dimension‑independent size.

By Murtaza Rangwala, Farag Azzedin, Richard O. Sinnott, Rajkumar Buyya
llmsfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Aug 27

Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

The paper investigates how adversarial examples transfer between client models in federated learning and explores the relationship between these examples and client data distributions. It proposes a defense strategy based on adversarial training that leverages the transferability of model robustness. Experiments on real-life datasets demonstrate that the new attack and defense methods outperform existing state‑of‑the‑art approaches.

By Zuobin Xiong, Deval Mukherjee, Homook Cho, Wei Li
benchmarkssafety
More like this →