# Federated guard reduces multi-agent attack success in tests

_Friday, September 4, 2026 at 12:00 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers introduced FGLGuard, a federated graph-learning safety guard for LLM multi-agent systems, in an arXiv paper. The paper says operators train on private judge-labeled episode graphs and share model updates rather than traces. Across three benchmarks, it reports outperforming an in-domain centralized ceiling; in a live AgentDojo test, it cut ground-truth attack success by 43% with near-unguarded utility. The results are preprint findings, not an independently verified deployment.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2609.02967)

---
Canonical: https://techandbusiness.org/newswire/GeY-rmQBwSS_NlCQSCkKBw
Retrieved: 2026-09-05T02:43:27.145Z
Publisher: Tech & Business (techandbusiness.org)