Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing

arXiv:2610.12711 · cs.LG, cs.CR · Submitted 2026-10-08 · Read on arXiv

cs.LG, cs.CR

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/GuangLun2000/HMP-GAE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Hypergraph — 1× in this paper · explained in 2 episodes

Sources

• Graph Representation-based Model Poisoning on Federated Large Language Models
• Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends
• Federated Large Language Models: Current Progress and Future Directions
• LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning
• Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
• DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
• Qwen2.5-Coder Technical Report
• The Llama 3 Herd of Models
• Byzantine-Tolerant Machine Learning
• Mitigating Sybils in Federated Learning Poisoning
• FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks