Internet of Things (IoT) devices is vulnerable to assaults such as Darknet and blackhole attacks because of their restricted capabilities. Using the CIC-Darknet dataset, DarkWeb Traffic Detection System (DTDS) models are developed and evaluated using machine learning and deep learning techniques. Using DTDS models, we were able to identify and categories Darknet activity in IoT networks. Machine learning helps keep sensitive information safe and enhances network performance. When applied to Darknet data, DTDS models improve IoT security by identifying and classifying threats. IoT devices are vulnerable to cyberattacks like Darknet or blackhole attacks, is explored, and DTDS in IoTs effectiveness is assessed. The research concludes that DTDS models may be used to effectively detect and classify darknet traffic in IoT networks, leading to improved network services and data security. The performance of DTDS models was measured using accuracy, precision, recall, and F1-score, and the models were shown to be superior to their rivals.

Internet of Things, Machine Learning, Dark Web Traffic Detection System, Darknet