Abstract
Internet of Things (IoT) is a pervasively-used technology for the last few years. IoT technologies are also responsible for intensifying various everyday smart applications improving the standard of living. However, the inter-crossing of IoT systems and the multi-directional elements responsible for these systems' placement have raised new safety concerns. They generate and share a massive amount of sensitive data. Unfortunately, both the data and the devices are susceptible to many privacy and security challenges. Much research has been done to secure these infrastructures; however, Machine Learning (ML), among others, provides higher accuracy. This survey covers the major security issues and open challenges encountered by IoT infrastructures. It also encompasses an in-depth study and analysis of ML-based state-of-the-art solutions used in securing such domains. The security challenges and requirements in IoT-based systems have been highlighted, along with a discussion on how ML supports security measures in the said domain. Furthermore, the challenges associated with ML-based security solutions have been identified concerning IoT. An analysis of prevailing ML security techniques' constraints is also contemplated.
Original language | English |
---|---|
Pages (from-to) | 89-104 |
Number of pages | 16 |
Journal | Journal of Parallel and Distributed Computing |
Volume | 162 |
DOIs | |
Publication status | Published - 29 Jan 2022 |
Keywords
- Internet of Things
- Machine learning
- Security