发表机构
UTS-HCMUT JTIRC; Ho Chi Minh City University of Technology (HCMUT); Vietnam National University Ho Chi Minh City (VNU-HCM); University of Technology Sydney（UTS-HCMUT JTIRC; 胡志明市技术大学（HCMUT）; 越南国家大学胡志明市分校（VNU-HCM）; 悉尼科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异构物联网环境中现有PFL方法易过度个性化导致OOD攻击检测性能下降的问题，提出FBID框架，通过服务器端上下文多臂老虎机与信任混合机制，提升OOD检测率、F1值及对未知攻击的鲁棒性。
AI 中文摘要
个性化联邦学习（PFL）已成为异构物联网环境中入侵检测的有前景解决方案，因其可在高度非独立同分布（non-IID）数据分布下提升本地适配能力。然而，现有PFL方法常依赖客户端自我调整，可能导致过度个性化，进而使分布外（OOD）攻击检测性能大幅下降。本文提出联邦盗入侵检测（FBID），这是一种新型自适应PFL框架，通过服务器端个性化控制解决该局限。具体而言，FBID在服务器端采用上下文多臂老虎机，根据各客户端的观测行为与更新质量动态调节其本地训练强度；此外，FBID引入基于信任的混合机制，推导全局模型与本地模型间的客户端特定插值系数，在保留全局攻击检测知识的同时，仍允许有益的本地专业化。通过在CICIoT2023数据集上，于异构客户端分布与OOD压力测试设置下开展大量实验，结果表明，相较于最强稳定基线，FBID可将各客户端OOD检测率（DR）提升最高7.66%，F1值（F1）提升最高5.08%（相对值），同时增强对先前未见过的攻击类别的鲁棒性。
英文摘要
Personalized Federated Learning (PFL) has emerged as a promising solution for intrusion detection in heterogeneous IoT environments, as it can improve local adaptation under highly Non-Independent and Identically Distributed (non-IID) data distributions. However, existing PFL methods often rely on client-side self-adjustment, which may lead to over-personalization and substantial degradation in out-of-distribution (OOD) attack detection. In this paper, we propose Federated Bandit Intrusion Detection (FBID), a novel adaptive PFL framework to address this limitation through server-side personalization control. In particular, FBID employs a contextual multi-armed bandit at the server to dynamically regulate each client's local training intensity according to its observed behavior and update quality. Moreover, FBID introduces a trust-based blending mechanism to derive client-specific interpolation coefficients between the global and local models, thereby preserving global attack-detection knowledge while still allowing beneficial local specialization. Through extensive experiments on the CICIoT2023 dataset under heterogeneous client distributions and OOD stress-test settings, we show that FBID improves individual client OOD Detection Rate (DR) by up to 7.66% and F1-Score (F1) by up to 5.08% (relative) over the strongest stable baseline, while also improving robustness to previously unseen attack classes.
