摘要
由一名新闻记者-机器人与机器学习每日新闻编辑-研究人员详细介绍了人工智能的新数据。根据NewsRx J Ournalists在巴基斯坦旁遮普省的新闻报道，研究表明，"智能家居设备，也被称为物联网设备，提供了很大的便利；然而，它们也为Attac Kers提供了危及房主安全和隐私的机会。"这项研究的资助者包括英国格拉斯哥加里多尼亚大学计算机、工程和建筑环境学院网络安全和网络系。我们的新闻记者从伊斯兰堡COMSATS大学的研究中获得了一句话：“由于计算资源有限，保护这些物联网设备是一个艰巨的挑战。基于机器学习的入侵检测系统(IDSs)已经在边缘和云中实现；然而，IDSs还没有嵌入到物联网设备中。为了解决这个问题，针对智能家居物联网设备,提出了一种基于机器学习的双层入侵检测系统,提高了检测精度和计算效率。该入侵检测系统将数据上传到云服务器上的网站上,将第二层入侵检测系统部署在云服务器上进行攻击分类,该入侵检测系统在云级别(multiclassification)上可以检测出网络威胁,准确率为99.50%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in artific ial intelligence. According to news reporting from Punjab, Pakistan, by NewsRx j ournalists, research stated, "Smart home devices, also known as IoT devices, pro vide significant convenience; however, they also present opportunities for attac kers to jeopardize homeowners' security and privacy." Funders for this research include Department of Cyber Security And Networks, Sch ool of Computing, Engineering And Built Environment, Glasgow Caledonian Universi ty, Uk. Our news correspondents obtained a quote from the research from COMSATS Universi ty Islamabad: "Securing these IoT devices is a formidable challenge because of t heir limited computational resources. Machine learning-based intrusion detection systems (IDSs) have been implemented on the edge and the cloud; however, IDSs h ave not been embedded in IoT devices. To address this, we propose a novel machin e learning-based two-layered IDS for smart home IoT devices, enhancing accuracy and computational efficiency. The first layer of the proposed IDS is deployed on a microcontroller-based smart thermostat, which uploads the data to a website h osted on a cloud server. The second layer of the IDS is deployed on the cloud si de for classification of attacks. The proposed IDS can detect the threats with a n accuracy of 99.50% at cloud level (multiclassification)."
NETL
NSTL