A Paradigm Shift in IoT Cyber-Security: A Systematic Review

Abstract

Abstract: Internet of Things (IoT) describes physical gadgets with sensors, processing power, software and other technologies that connect with other devices and exchange data over the internet. Consumers and businesses everywhere are getting used to the notion that critical data processing and analysis are now being fulfilled by a new-age technology infrastructure. The Internet of Things (IoT) is the key driver of this trend, with 64 billion IoT devices estimated around the world by 2026. IoT activities span everything from smart homes and smart cities to fitness monitoring and inventory control. This rapid growth of IoT has its own set of challenges and the first one being the threat of cybersecurity. As the Internet of Things rapidly grows, cyber threats and associated risks continue to evolve and become increasingly complex. The biggest threat to these IoT devices, which has grown exponentially in the past few years, is the Distributed Denial of Service (DDoS). This highly daunting cyber-threat is extremely dangerous because perpetrators can now use IoT devices to make the attacks more severe. The formation of botnet clusters (hijacked IoT devices) is the heart of a large-scale DDoS cyber-attack. This research work focuses on the emerging trends associated with the volume of cyber-attacks. Furthermore, the research delves into the possible solutions to tackle, and possibly eradicate the cyber-threats present in the IoT systems. The domain of Machine Learning is investigated thoroughly in order to extract the ongoing research and possible solutions pertaining to the cyber-security of IoT devices and systems.