【Author】
Hei, Xinhong; Yin, Xinyue; Wang, Yichuan; Ren, Ju; Zhu, Lei
【Source】COMPUTERS & SECURITY
【Abstract】With the rapid development of IoT technology, millions of physical devices embedded with electronics or software are put into regular production. Each IoT device is connected to the user's life and property privacy. Without a credible intrusion detection and defense mechanism installed on the device, it may be attacked by hackers, such as monitoring events of home cameras and control of smart devices. These attack events will have a serious impact on users' production and life. This paper proposes a Blockchained-Federated Learning based cloud intrusion detection scheme. The scheme sends the local training parameters of the IoT intrusion alarm set to the cloud computing center for global prediction, and stores the model training process information and behavior on the blockchain. In order to solve the high probability of false alerts affecting the accuracy of the federated learning model, the scheme proposes an alert filter identification module. At the same time, through the erasure code-based blockchain storage solution, the traditional blockchain storage performance is improved to meet the storage needs of a large number of alert training data in real scenarios. (C) 2020 Elsevier Ltd. All rights reserved.
【Keywords】IoT; Cloud security; Privacy protection; Federated learning; Blockchain
【标题】用于分布式恶意攻击检测的可信特征聚合器联邦学习
【摘要】随着物联网技术的快速发展，数以百万计的嵌入电子或软件的物理设备投入正常生产。每一个物联网设备都连接着用户的生命财产隐私。如果设备上没有安装可信的入侵检测和防御机制，就有可能受到黑客的攻击，例如监控家庭摄像头事件和控制智能设备。这些攻击事件将对用户的生产生活造成严重影响。本文提出了一种基于区块链联邦学习的云入侵检测方案。该方案将物联网入侵报警集的本地训练参数发送到云计算中心进行全局预测，并将模型训练过程信息和行为存储在区块链上。为了解决高概率的误报影响联邦学习模型准确性的问题，该方案提出了一个警报过滤器识别模块。同时，通过基于纠删码的区块链存储方案，提升传统区块链存储性能，满足真实场景下大量告警训练数据的存储需求。 (C) 2020 Elsevier Ltd. 保留所有权利。
【关键词】物联网；云安全；隐私保护;联邦学习；区块链
评论