Название: Big Data Analytics in Fog-Enabled IoT Networks: Towards a Privacy and Security Perspective
Автор: Govind P. Gupta, Rakesh Tripathi, Brij B. Gupta, Kwok Tai Chui
Издательство: CRC Press
Год: 2023
Страниц: 233
Язык: английский
Формат: pdf (true)
Размер: 31.5 MB

The integration of fog computing with the resource-limited Internet of Things (IoT) network formulates the concept of the fog-enabled IoT system. Due to a large number of IoT devices, the IoT is a main source of Big Data. A large volume of sensing data is generated by IoT systems such as smart cities and smart-grid applications. A fundamental research issue is how to provide a fast and efficient data analytics solution for fog-enabled IoT systems. Big Data Analytics in Fog-Enabled IoT Networks: Towards a Privacy and Security Perspective focuses on Big Data analytics in a fog-enabled-IoT system and provides a comprehensive collection of chapters that touch on different issues related to healthcare systems, cyber-threat detection, malware detection, and the security and privacy of IoT Big Data and IoT networks.

This book also emphasizes and facilitates a greater understanding of various security and privacy approaches using advanced Artificial Intelligence and Big Data technologies such as Machine Learning and Deep Learning, Federated Learning, blockchain, and edge computing, as well as the countermeasures to overcome the vulnerabilities of the fog-enabled IoT system.

Many organizations and industries are facing the problem of growing cyber-attacks. Malware are the programmes that, when executed, can destroy the function of a system. Malware can be classified on the basis of behaviour and execute itself as adware, spyware, worms, Trojans, viruses, rootkits, backdoors, ransomware, and browser hijackers. Computer and mobile systems are attacked to destroy resources, steal sensitive information, and user credentials. For detecting malware in Machine Learning (ML), the local data is collected in one aggregated server. This leads to the violation of privacy, which can be solved by using Federated Learning (FL), which allows for the detection of malware when local data is at the device.