arXiv cs.AI· Kiranmayee Janardhan, Karthick S, Madhusmita Panda, Bharathi Vokkaliga Ganesh, Syed Ahmed·· 2 小时前AI 评分20
面向多智能体 AI 系统的治理感知联邦学习：可信协作 AI 的策略驱动框架 GAFL
Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
AI 导读
一篇 arXiv 论文提出治理感知联邦学习框架 GAFL，在常规联邦学习上增加治理证据独立验证、时间信任、公平性评估、异常检测与防篡改审计日志。
正文 · 原文
Abstract:Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fairness assessment, explainability monitoring, and auditability. This paper proposes Governance-Aware Federated Learning (GAFL), which combines independent governance-evidence verification, temporal trust, fairness and explanation assessment, anomaly detection, policy enforcement, normalized aggregation, and tamper-evident audit logging. Client-reported governance values are authenticated, bound to their submitted model updates, and independently recomputed before aggregation. A cross-silo prototype with 10 participants was evaluated on the Adult Income dataset under honest, benign non-IID, biased-data, malicious-update, non-compliant, falsified-evidence, and mixed-threat scenarios. Four methods were compared across five random seeds: FedAvg, FedAvg with anomaly filtering, GAFL without independent verification, and complete GAFL. Complete GAFL intervened on all affected participants at the final round across the evaluated risk scenarios, including identifying 100% of falsified-evidence participants, whereas GAFL without verification identified none of the falsified-evidence participants. Final macro-F1 ranged from 0.7520 to 0.7733 across GAFL scenarios. Complete GAFL required 173.67 plus or minus 26.94 ms of governance processing per round, compared with 3.82 plus or minus 0.79 ms for FedAvg. A strict demographic-parity threshold also caused frequent interventions for honest participants, demonstrating a significant fairness-policy and utility trade-off.
| Comments: | 16 pages, 2 Figures and 3 Tables presented at NGEN 2026 Conference |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38411 [cs.AI] |
| (or arXiv:2610.38411v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38411 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kiranmayee Janardhan Dr [view email]
[v1]
Wed, 28 Oct 2026 07:57:10 UTC (610 KB)
来源：arXiv cs.AI · arxiv.org