Abstract:
With its exponential growth, the Internet of Things (IoT) has produced unprecedented levels of connectivity and data. Anomaly detection is a security feature that identifies instances in which system behavior deviates from the expected norm, facilitating the prompt identification and resolution of anomalies. When AI and the IoT are combined, anomaly detection becomes more effective, enhancing the reliability, efficacy, and integrity of IoT systems. AI-based anomaly detection systems are capable of identifying a wide range of threats in IoT environments, including brute force, buffer overflow, injection, replay attacks, DDoS assault, SQL injection, and back-door exploits. Intelligent Intrusion Detection Systems (IDSs) are imperative in IoT devices, which help detect anomalies or intrusions in a network, as the IoT is increasingly employed in several industries but possesses a large attack surface which presents more entry points for attackers. This study reviews the literature on anomaly detection in IoT infrastructure using machine learning and deep learning. This paper discusses the challenges in detecting intrusions and anomalies in IoT systems, highlighting the increasing number of attacks. It reviews recent work on machine learning and deep-learning anomaly detection schemes for IoT networks, summarizing the available literature. From this survey, it is concluded that further development of current systems is needed by using varied datasets, real-time testing, and making the systems scalable.
摘要:
随着它的指数增长,物联网(IoT)产生了前所未有的连接和数据水平。异常检测是一种安全功能,用于识别系统行为偏离预期规范的实例,便于及时识别和解决异常情况。当AI和物联网结合在一起时,异常检测变得更加有效,提高可靠性,功效,物联网系统的完整性。基于AI的异常检测系统能够识别物联网环境中的各种威胁,包括蛮力,缓冲区溢出,注射,重播攻击,DDoS攻击,SQL注入,和后门漏洞。智能入侵检测系统(IDS)在物联网设备中势在必行,这有助于检测网络中的异常或入侵,随着物联网在多个行业中的应用越来越多,但拥有庞大的攻击面,为攻击者提供了更多的切入点。本研究回顾了使用机器学习和深度学习在物联网基础设施中进行异常检测的文献。本文讨论了在物联网系统中检测入侵和异常的挑战,越来越多的攻击。它回顾了物联网网络机器学习和深度学习异常检测方案的最新工作。总结现有文献。从这次调查来看,结论是,需要通过使用不同的数据集来进一步开发当前的系统,实时测试,并使系统可扩展。