Security of Big Data over IoT Environment by Integration of Deep Learning and Optimization
| Autor: | N.Noor Alleema, Ramakrishnan Raman, Fidel Castro-Cayllahua, Vinod Motiram Rathod, Juan Carlos Cotrina-Aliaga, Supriya Sanjay Ajagekar, Reshma Ramakant Kanse |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | International Journal of Communication Networks and Information Security (IJCNIS). 14:203-221 |
| ISSN: | 2073-607X 2076-0930 |
| Popis: | This is especially true given the spread of IoT, which makes it possible for two-way communication between various electronic devices and is therefore essential to contemporary living. However, it has been shown that IoT may be readily exploited. There is a need to develop new technology or combine existing ones to address these security issues. DL, a kind of ML, has been used in earlier studies to discover security breaches with good results. IoT device data is abundant, diverse, and trustworthy. Thus, improved performance and data management are attainable with help of big data technology. The current state of IoT security, big data, and deep learning led to an all-encompassing study of the topic. This study examines the interrelationships of big data, IoT security, and DL technologies, and draws parallels between these three areas. Technical works in all three fields have been compared, allowing for the development of a thematic taxonomy. Finally, we have laid the groundwork for further investigation into IoT security concerns by identifying and assessing the obstacles inherent in using DL for security utilizing big data. The security of large data has been taken into consideration in this article by categorizing various dangers using a deep learning method. The purpose of optimization is to raise both accuracy and performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|