paperSeptember 2026Unreviewed

Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning

Jinxi Yu, Eric Hanchen Jiang, Levina Li, Dong Liu, Zhi Zhang, Wenxiao Zhao, Yanxuan Yu, Kai-Wei Chang, Ying Nian Wu

Abstract

Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and intervene on the topology---but they assume one operator can pool all labeled traces. Across organizations that assumption breaks: episodes contain private prompts, tool outputs, and proprietary workflows, and no silo alone sees the full attack distribution. We cast privacy-preserving MAS safeguarding as graph federated learning and instantiate FGLG

Cite

@misc{yu2026privacypreserving,
  title = {{Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning}},
  author = {Jinxi Yu and Eric Hanchen Jiang and Levina Li and Dong Liu and Zhi Zhang and Wenxiao Zhao and Yanxuan Yu and Kai-Wei Chang and Ying Nian Wu},
  year = {2026},
  month = sep,
  eprint = {2609.02967},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02967}
}