A Research on Efficient Spam Detection Technique for Iot Devices Using Machine Learning

• Published in: NeuroQuantology Vol. 20; no. 18; p. 625
• Main Authors: Aijaz Ali Khan, Mulajkar, Rahul M, Khan, Vajid N, Sonkar, Shrinivas K, Takale, Dattatray G
• Format: Journal Article
• Language: English
• Published: Bornova Izmir NeuroQuantology 01.01.2022
• Subjects: Algorithms; Anomalies; Cybersecurity; Internet of Things; Machine learning
• ISSN: 1303-5150
• DOI: 10.48047/NQ.2022.20.18.NQ88057

Internet of Things (IoT) refers to the worldwide network of billions of objects, both stationary and mobile, equipped with electronics to gather and send data. Over the last decade, the number of connected devices has increased exponentially, and by 2020, it is estimated that more than 25 billion devices will be online. In the next years, the quantity of data produced by these devices will skyrocket. The data produced by IoT devices comes in a wide range of forms, and the quality of that data is measured in terms of how quickly it can be accessed and how accurately it can be located. There's also something to think about, especially as the data produced by these devices increases. Through anomaly detection and guaranteeing security and permissions based on biotechnology, the use of machine learning (ML) algorithms in this setting has the potential to significantly improve the usability and security of IoT systems. On the other hand, hackers often see learning algorithms as a tool to exploit vulnerabilities in otherwise secure smart IoT-based systems.