From smart home to industrial automation to smart power grid, IoT- based solutions penetrate into every working field. These devices expand the attack surface and turned out to be an easy target for the attacker as resource constraint nature hinders the integration of heavy security solutions. Because IoT devices are less secured and operate mostly in unattended scenario, they perfectly justify the requirements of attacker to form botnet army to trigger Denial of Service attack on massive scale. Therefore, this paper presents a Machine Learning-based attack detection approach to identify the attack traffic in Consumer IoT (CIoT). This approach operates on local IoT network-specific attributes to empower low-cost machine learning classifiers to detect attack, at the local router. The experimental outcomes unveiled that the proposed approach achieved the highest accuracy of 0.99 which confirms that it is robust and reliable in IoT networks.
