[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2279":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"view_count":31,"doi":32,"paper":33,"created_at":62},2279,"Communication-efficient Federated Transfer Learning for real-time intrusion detection in agricultural IoT systems","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112411","The rapid deployment of Agricultural Internet of Things (Ag-IoT) networks has introduced significant security challenges, mainly due to their limited computational resources and operation in remote environments. These constraints, combined with the critical nature of agricultural data and operations, make Ag-IoT systems particularly vulnerable to cyber threats, thus requiring robust, efficient security mechanisms. In this context, Intrusion Detection Systems (IDS) play a crucial role in monitoring network activities and detecting malicious behavior. However, conventional IDS solutions often suffer from high computational overhead, increased latency, and substantial communication costs. Although Federated Learning (FL) enhances data privacy by enabling distributed model training, its efficiency remains constrained in resource-limited Ag-IoT scenarios. To overcome these limitations, we propose a novel IDS based on Federated Transfer Learning (FTL) for multiclass network intrusion classification, which integrates FL with lightweight pretrained image models. The key idea of our approach is to transform network traffic data into grayscale images, allowing the reuse of efficient computer vision models. This transformation reduces data complexity, which is expected to support low-resource training and inference on edge devices. The FTL framework ensures that only model updates are exchanged, minimizing communication overhead while preserving data privacy. Experimental results, validated over three independent runs (Mean ± SD), demonstrate that our approach achieves 99.96% ± 0.00% accuracy on the Edge-IIoTset and 99.96% ± 0.01% accuracy on the Farm-Flow dataset. These findings highlight the strong theoretical potential of our FTL-based IDS as a promising candidate to enable intrusion detection in real-time, resource-efficient, and privacy-preserving Ag-IoT networks.","农业物联网(Ag-IoT)网络的快速部署带来了显著的安全挑战，这主要源于其有限的计算资源和在偏远环境中的运行条件。这些限制，加之农业数据和操作的关键性，使Ag-IoT系统特别容易受到网络威胁，因此需要稳健、高效的安全机制。在此背景下，入侵检测系统(IDS)在监控网络活动和检测恶意行为方面发挥着至关重要的作用。然而，传统IDS解决方案往往面临高计算开销、延迟增加和大量通信成本的问题。尽管联邦学习(FL)通过支持分布式模型训练增强了数据隐私，但其效率在资源受限的Ag-IoT场景中仍然受到制约。为克服这些局限，我们提出了一种基于联邦迁移学习(FTL)的新型IDS，用于多类网络入侵分类，该方案将FL与轻量级预训练图像模型相结合。我们方法的核心思想是将网络流量数据转换为灰度图像，从而能够复用高效的计算机视觉模型。这种转换降低了数据复杂度，有望支持边缘设备上的低资源训练和推理。FTL框架确保仅交换模型更新，在保持数据隐私的同时最大限度地减少通信开销。实验结果表明，在三次独立运行验证下(均值±标准差)，我们的方法在Edge-IIoTset上达到99.96%±0.00%的准确率，在Farm-Flow数据集上达到99.96%±0.01%的准确率。这些发现凸显了基于FTL的IDS在实现实时、资源高效且隐私保护的Ag-IoT网络入侵检测方面具有强大的理论潜力。",null,"Computers and Electronics in Agriculture","2026-09-12T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"提出联邦迁移学习入侵检测方法，将流量转为灰度图复用轻量视觉模型，在Edge-IIoTset与Farm-Flow上达99.96%精度，兼顾实时性、低通信开销与隐私保护，对农业物联网安全有较强参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","农业物联网","联邦学习","网络安全",0,"10.1016\u002Fj.compag.2026.112411",{"doi":32,"openalex_id":34,"authors":35,"venue":10,"cited_by_count":31,"oa_url":6,"card":55,"direction":59,"ingested_from":61},"W7212387370",[36,39,42,45,48,50,52],{"name":37,"orcid":38},"Amina Khacha","https:\u002F\u002Forcid.org\u002F0009-0009-3299-8622",{"name":40,"orcid":41},"Zibouda Aliouat","https:\u002F\u002Forcid.org\u002F0000-0002-7007-7607",{"name":43,"orcid":44},"Yasmine Harbi","https:\u002F\u002Forcid.org\u002F0000-0001-6731-7895",{"name":46,"orcid":47},"Chirihane Gherbi","https:\u002F\u002Forcid.org\u002F0000-0002-0551-3978",{"name":49,"orcid":9},"Rafika Saadouni",{"name":51,"orcid":9},"Ado Adamou ABBA ARI",{"name":53,"orcid":54},"Hakim Mabed","https:\u002F\u002Forcid.org\u002F0000-0001-8358-4029",{"tldr":56,"method":57,"finding":58,"direction":59,"opportunity":60},"提出联邦迁移学习入侵检测方法，将流量转灰度图复用轻量视觉模型，实现农业物联网实时检测。","联邦迁移学习+轻量预训练图像模型，流量转灰度图，Edge-IIoTset与Far","在Edge-IIoTset和Farm-Flow上均达99.96%准确率，通信开销低且保护隐私。","智慧农业 \u002F 农业物联网","可探索真实Ag-IoT边缘设备部署与动态异构流量下的联邦迁移学习鲁棒性及通信压缩优化。","openalex","2026-09-13T23:30:01.631534Z"]