Cyber attacks detection in Internet of Things technology using Deep Learning algorithms
The Internet of Things (IoTs) is a distributed and complex paradigm that consists of billions of smart devices connected to the internet. Interconnected devices act as intelligent systems to provide services, open new horizons to share data and enhance business opportunities.
The diverse services provided by the IoT has greatly impacted every aspect of life. However, IoT devices are prone to a number of cyber-security attacks including the Distributed Denial of Service (DDoS) .
The DDoS attack is a malicious attempt to exhaust and disrupt the normal operation of a network, server, or infrastructure, whether it is a corporate, governmental, or any other private/public entities .
Nowadays, DDoS has become one of the most serious and widely used attacks to shutdown web servers and network systems. The attackers, whether they are state or non-state actors, harness the capabilities to compromise a pool of IoT devices and create and control botnets or zombies, in order to launch a large-scale attack to exhaust resources and prevent legitimate users from accessing services, causing significant downtime/disruption .
Securing IoT systems has become a daunting task, and traditional cyber-security solutions have become ineffective or unsuitable to IoT environments due to their low power, low storage capacity and low processing capability. Insecure protocols and the distributed nature of IoT networks have become an extremely hostile environment in the cyber sphere. The need to develop smart and light-weight security solutions to detect and mitigate DDoS attacks on IoT networks  is crucial.
Studies  have shown that artificial intelligence (AI)/machine learning (ML)-based techniques, such as Deep Learning (DL), have proven their capabilities when dealing with mass data generating systems, such as IoT networks. This paper first investigates the suitability of traditional ML solutions, such Naïve Bayes, Support Vector Machines (SV
Get Fresh Answer: 100% Plagiarism Free & Custom Written, Tailored to your instructions