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.
By Edoardo Gabrielli, Gabriele Tolomei
arXiv:2609.07312v1 Announce Type: new
Abstract: This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attack...
By Xiao Ma, Hong Shen, Hui Tian, Wenqi Lyu, Wei Ke
arXiv:2607. 08651v1 Announce Type: new Abstract: Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to Byzantine or lazy participants.
By Amirhossein Taherpour, Xiaodong Wang
The paper proposes Byrd-NAFL, a Byzantine‑robust federated learning algorithm that incorporates Nesterov’s momentum and resilient aggregation rules. It achieves fast and safe convergence under non‑convex, smooth loss functions with relaxed gradient assumptions, and provides a finite‑time convergence guarantee. Experiments show that Byrd-NAFL outperforms existing methods in convergence speed, accuracy, and resilience to various malicious attacks.
By Lihan Xu, Xiaoyi Fan, Gang Wang, Runhao Zeng, Xiping Hu, Yanjie Dong
Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors.
SeedFlood is a novel decentralized fine‑tuning method for large language models that scales to billions of parameters and hundreds of clients. It leverages the seed‑reconstructible structure of zeroth‑order gradients to reduce message sizes to near‑zero, enabling efficient flooding across the network. Experiments show SeedFlood outperforms standard zeroth‑order baselines in communication efficiency and generalization, and rivals first‑order gossip methods while incurring far less communication cost.
By Jihun Kim, Dongyeop Lee, Namhoon Lee
arXiv:2606. 19129v1 Announce Type: cross Abstract: Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem.
By Ousmane Touat, C\'esar Sabater, Mohamed Maouche, Sonia Ben Mokhtar
arXiv:2608.21137v1 Announce Type: new
Abstract: Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model...
By Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han
arXiv:2608. 06946v1 Announce Type: cross Abstract: In gossip learning, a network of nodes trains a shared model collaboratively, without a central coordinator, by repeatedly exchanging parts of their local models.
By Fabien Mathieu (NPA), Alexandre Pham (NPA), Maria Gradinariu Potop-Butucaru (NPA), S{\'e}bastien Tixeuil (IUF, NPA)
arXiv:2405. 07708v3 Announce Type: replace Abstract: Decentralized learning (DL) enables participants to collaboratively train models without a central server, yet it faces significant scalability challenges that demand sparsification to reduce the prohibitive communication costs of peer-to-peer exchange.
By Sayan Biswas, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Milos Vujasinovic
arXiv:2609.25701v1 Announce Type: new
Abstract: We study distributed Byzantine-resilient actor-critic multi-agent reinforcement learning (AC-MARL), where agents collectively learn policies through lo...
By Haejoon Lee, Dimitra Panagou
arXiv:2412. 07151v1 Announce Type: cross Abstract: Distributed model training needs to be adapted to challenges such as the straggler effect and Byzantine attacks.
By Jiahe Yan, Pratik Chaudhari, Leonard Kleinrock